ai-research-survey

citation-graph.json (349556B)

---

 {
   "node_count": 572,
   "edge_count": 2030,
   "nodes": [
     {
       "id": "2025-ai-agent-2026",
       "title": "The 2025 AI Agent Index"
     },
     {
       "id": "3dshape2vecset-3d-shape-2023",
       "title": "3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models"
     },
     {
       "id": "a2hcoder-llmdriven-coding-2025",
       "title": "A2H-MAS: An Algorithm-to-HLS Multi-Agent System for Automated and Reliable FPGA Implementation"
     },
     {
       "id": "aart-aiassisted-redteaming-2023",
       "title": "AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications"
     },
     {
       "id": "acar-adaptive-complexity-2026",
       "title": "ACAR: Adaptive Complexity Routing for Multi-Model Ensembles with Auditable Decision Traces"
     },
     {
       "id": "accelerating-automatic-program-2025",
       "title": "Accelerating Automatic Program Repair with Dual Retrieval-Augmented Fine-Tuning and Patch Generation on Large Language Models"
     },
     {
       "id": "accelerating-large-language-2023",
       "title": "Accelerating Large Language Model Decoding with Speculative Sampling"
     },
     {
       "id": "across-programming-language-2025",
       "title": "Across Programming Language Silos: A Study on Cross-Lingual Retrieval-augmented Code Generation"
     },
     {
       "id": "adafuse-adaptive-ensemble-2026",
       "title": "AdaFuse: Adaptive Ensemble Decoding with Test-Time Scaling for LLMs"
     },
     {
       "id": "adaplanner-adaptive-planning-2023",
       "title": "AdaPlanner: Adaptive Planning from Feedback with Language Models"
     },
     {
       "id": "adaptevolve-improving-efficiency-2026",
       "title": "AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection"
     },
     {
       "id": "adapting-knowledge-prompt-2025",
       "title": "Adapting Knowledge Prompt Tuning for Enhanced Automated Program Repair"
     },
     {
       "id": "adaptive-attacks-break-2025",
       "title": "Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents"
     },
     {
       "id": "adaptive-attacks-bypass-defenses-2025",
       "title": "The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against LLM Jailbreaks and Prompt Injections"
     },
     {
       "id": "adaptive-data-augmentation-2026",
       "title": "Adaptive Data Augmentation with Multi-armed Bandit: Sample-Efficient Embedding Calibration for Implicit Pattern Recognition"
     },
     {
       "id": "adaptive-selftriggered-control-2023",
       "title": "Adaptive Self-Triggered Control for Multi-Agent Systems with Actuator Failures and Time-Varying State Constraints"
     },
     {
       "id": "adaptive-test-generation-2023",
       "title": "An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation"
     },
     {
       "id": "adaptive-visionbased-coverage-2025",
       "title": "Adaptive Vision-Based Coverage Optimization in Mobile Wireless Sensor Networks: A Multi-Agent Deep Reinforcement Learning Approach"
     },
     {
       "id": "adaptrack-constrained-decoding-2025",
       "title": "AdapTrack: Constrained Decoding without Distorting LLM's Output Intent"
     },
     {
       "id": "adas-automated-design-2024",
       "title": "Automated Design of Agentic Systems"
     },
     {
       "id": "adoption-generative-artificial-2026",
       "title": "Adoption of Generative Artificial Intelligence in the German Software Engineering Industry: An Empirical Study"
     },
     {
       "id": "advancements-generative-ai-2023",
       "title": "Advancements in Generative AI: A Comprehensive Review of GANs, GPT, Autoencoders, Diffusion Model, and Transformers"
     },
     {
       "id": "advancements-software-engineering-2024",
       "title": "Advancements in software engineering using AI"
     },
     {
       "id": "advancing-code-generation-2025",
       "title": "Towards Advancing Code Generation with Large Language Models: A Research Roadmap"
     },
     {
       "id": "advancing-engineering-research-2025",
       "title": "Advancing engineering research through context-aware and knowledge graph–based retrieval-augmented generation"
     },
     {
       "id": "advancing-language-model-2025",
       "title": "T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling"
     },
     {
       "id": "advancing-largemolecule-discovery-2025",
       "title": "Advancing large-molecule discovery with a unified digital platform for data analysis and workflow management"
     },
     {
       "id": "advancing-llm-safe-2025",
       "title": "Advancing LLM Safe Alignment with Safety Representation Ranking"
     },
     {
       "id": "advancing-methodological-development-2025",
       "title": "Advancing methodological development of artificial intelligence in patient-centered comparative clinical effectiveness research: Patient-Centered Outcomes Research Institute's unique contribution to research done differently"
     },
     {
       "id": "advancing-nursing-regulation-2025",
       "title": "Advancing nursing regulation in the digital era: Harnessing AI to bridge workforce gaps and strengthen practice competency and safety"
     },
     {
       "id": "advancing-software-quality-2025",
       "title": "Advancing Software Quality: A Standards-Focused Review of LLM-Based Assurance Techniques"
     },
     {
       "id": "adversarial-bug-reports-2025",
       "title": "Adversarial Bug Reports as a Security Risk in Language Model-Based Automated Program Repair"
     },
     {
       "id": "adversarial-threat-vectors-2025",
       "title": "Adversarial Threat Vectors and Risk Mitigation for Retrieval-Augmented Generation Systems"
     },
     {
       "id": "advevomarl-shaping-internalized-2025",
       "title": "AdvEvo-MARL: Shaping Internalized Safety Through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning"
     },
     {
       "id": "aegaeon-effective-gpu-2025",
       "title": "Aegaeon: Effective GPU Pooling for Concurrent LLM Serving on the Market"
     },
     {
       "id": "aegis-automated-coevolutionary-2025",
       "title": "AEGIS: Automated Co-Evolutionary Framework for Guarding Prompt Injection"
     },
     {
       "id": "aegis20-diverse-ai-2025",
       "title": "AEGIS2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails"
     },
     {
       "id": "aegisagent-autonomous-defense-2025",
       "title": "AegisAgent: An Autonomous Defense Agent Against Prompt Injection Attacks in LLM-HARs"
     },
     {
       "id": "african-woman-rhythmic-2024",
       "title": "The African Woman is Rhythmic and Soulful: An Investigation of Implicit Biases in LLM Open-ended Text Generation"
     },
     {
       "id": "agent-contracts-formal-2026",
       "title": "Agent Contracts: A Formal Framework for Resource-Bounded Autonomous AI Systems"
     },
     {
       "id": "agent-developer-practices-2025",
       "title": "An Empirical Study of Agent Developer Practices in AI Agent Frameworks"
     },
     {
       "id": "agent-error-taxonomy-2025",
       "title": "Where LLM Agents Fail and How They Can Learn from Failures"
     },
     {
       "id": "agent-security-bench-2024",
       "title": "Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-Based Agents"
     },
     {
       "id": "agentasajudge-evaluate-agents-2024",
       "title": "Agent-as-a-Judge: Evaluate Agents with Agents"
     },
     {
       "id": "agentask-multiagent-systems-2025",
       "title": "AGENTASK: Multi-Agent Systems Need to Ask"
     },
     {
       "id": "agentbased-evaluation-framework-2025",
       "title": "An Agent-based Evaluation Framework for Complex Code Generation"
     },
     {
       "id": "agentbench-evaluating-llms-2023",
       "title": "AgentBench: Evaluating LLMs as Agents"
     },
     {
       "id": "agentdojo-dynamic-environment-2024",
       "title": "AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents"
     },
     {
       "id": "agentfm-roleaware-failure-2025",
       "title": "AgentFM: Role-Aware Failure Management for Distributed Databases with LLM-Driven Multi-Agents"
     },
     {
       "id": "agentfuzzer-generic-blackbox-2025",
       "title": "AGENTVIGIL: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents"
     },
     {
       "id": "agentic-adoption-github-2026",
       "title": "Agentic Much? Adoption of Coding Agents on GitHub"
     },
     {
       "id": "agentic-ai-architectures-2026",
       "title": "Agentic Artificial Intelligence (AI): Architectures, Taxonomies, and Evaluation of Large Language Model Agents"
     },
     {
       "id": "agentic-ai-assessment-framework-2025",
       "title": "Beyond Task Completion: An Assessment Framework for Evaluating Agentic AI Systems"
     },
     {
       "id": "agentic-ai-modernization-2026",
       "title": "Agentic AI Modernization: Transforming Institutional Infrastructure Through Orchestrated Multi-Agent LLM Framework"
     },
     {
       "id": "agentic-ai-security-survey-2025",
       "title": "Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges"
     },
     {
       "id": "agentic-ai-software-2025",
       "title": "Agentic AI for Software: thoughts from Software Engineering community"
     },
     {
       "id": "agentic-ai-software-2025-2",
       "title": "Agentic AI Software Engineers: Programming with Trust"
     },
     {
       "id": "agentic-bug-reproduction-2025",
       "title": "Agentic Bug Reproduction for Effective Automated Program Repair at Google"
     },
     {
       "id": "agentic-memory-learning-2026",
       "title": "Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents"
     },
     {
       "id": "agentic-programming-survey-2025",
       "title": "AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities"
     },
     {
       "id": "agentic-refactoring-empirical-2025",
       "title": "Agentic Refactoring: An Empirical Study of AI Coding Agents"
     },
     {
       "id": "agentic-software-engineering-2025",
       "title": "Toward Agentic Software Engineering Beyond Code: Framing Vision, Values, and Vocabulary"
     },
     {
       "id": "agentless-2024",
       "title": "AGENTLESS: Demystifying LLM-based Software Engineering Agents"
     },
     {
       "id": "agentmesh-cooperative-multiagent-2025",
       "title": "AgentMesh: A Cooperative Multi-Agent Generative AI Framework for Software Development Automation"
     },
     {
       "id": "agents-of-chaos-2026",
       "title": "Agents of Chaos"
     },
     {
       "id": "agents4plc-automating-closedloop-2024",
       "title": "Agents4PLC: Automating Closed-loop PLC Code Generation and Verification in Industrial Control Systems using LLM-based Agents"
     },
     {
       "id": "agentsllm-augmentative-generation-2025",
       "title": "AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework"
     },
     {
       "id": "agentsnet-coordination-collaborative-2025",
       "title": "AGENTSNET: Coordination and Collaborative Reasoning in Multi-Agent LLMs"
     },
     {
       "id": "agentspawn-adaptive-multiagent-2026",
       "title": "AgentSpawn: Adaptive Multi-Agent Collaboration Through Dynamic Spawning for Long-Horizon Code Generation"
     },
     {
       "id": "agenttypo-adaptive-typographic-2025",
       "title": "AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents"
     },
     {
       "id": "agentvigil-generic-blackbox-2025",
       "title": "AGENTVIGIL: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents"
     },
     {
       "id": "agint-agentic-graph-2025",
       "title": "Agint: Agentic Graph Compilation for Software Engineering Agents"
     },
     {
       "id": "ai-agents-software-2025",
       "title": "AI Agents in Software Engineering Optimizing Software Development Processes and Enhancing Security Management in Learning Management Systems"
     },
     {
       "id": "ai-alignment-contemporary-2025",
       "title": "AI Alignment: A Comprehensive Survey"
     },
     {
       "id": "ai-alignment-strategies-2025",
       "title": "AI Alignment Strategies from a Risk Perspective: Independent Safety Mechanisms or Shared Failures?"
     },
     {
       "id": "ai-as-cognitive-2025",
       "title": "AI as Cognitive Amplifier: Rethinking Human Judgment in the Age of Generative AI"
     },
     {
       "id": "ai-assistance-legal-2023",
       "title": "AI Assistance in Legal Analysis: An Empirical Study"
     },
     {
       "id": "ai-code-generators-2024",
       "title": "AI Code Generators for Security: Friend or Foe?"
     },
     {
       "id": "ai-code-maintainability-registered-report-2024",
       "title": "Does Co-Development with AI Assistants Lead to More Maintainable Code? A Registered Report"
     },
     {
       "id": "ai-code-not-reproducible-2025",
       "title": "AI-Generated Code Is Not Reproducible (Yet): An Empirical Study of Dependency Gaps in LLM-Based Coding Agents"
     },
     {
       "id": "ai-code-review-2025",
       "title": "AI Code Review Assistant: A Modern Web Based Solution for Automated Code Analysis and Developer Productivity Enhancement"
     },
     {
       "id": "ai-code-survival-open-source-2026",
       "title": "Will It Survive? Deciphering the Fate of AI-Generated Code in Open Source"
     },
     {
       "id": "ai-code-wild-2025",
       "title": "AI Code in the Wild: Measuring Security Risks and Ecosystem Shifts of AI-Generated Code in Modern Software"
     },
     {
       "id": "ai-ides-vs-agents-impact-2026",
       "title": "AI IDEs or Autonomous Agents? Measuring the Impact of Coding Agents on Software Development"
     },
     {
       "id": "ai-inference-falling-costs-2025",
       "title": "The Price of Progress: Algorithmic Efficiency and the Falling Cost of AI Inference"
     },
     {
       "id": "ai-nonmem-coding-2025",
       "title": "AI for NONMEM Coding in Pharmacometrics Research and Education: Shortcut or Pitfall?"
     },
     {
       "id": "ai-productivity-index-2025",
       "title": "The AI Productivity Index: APEX-v1-extended"
     },
     {
       "id": "ai-prs-code-quality-reuse-2026",
       "title": "More Code, Less Reuse: Investigating Code Quality and Reviewer Sentiment towards AI-generated Pull Requests"
     },
     {
       "id": "ai-safety-subproblems-2023",
       "title": "AI Safety Subproblems for Software Engineering Researchers"
     },
     {
       "id": "ai-scientist-fully-2024",
       "title": "The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery"
     },
     {
       "id": "ai-scientistv2-workshoplevel-2025",
       "title": "The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search"
     },
     {
       "id": "ai-software-engineering-2023",
       "title": "AI in Software Engineering: A Survey on Project Management Applications"
     },
     {
       "id": "ai-software-engineering-2023-2",
       "title": "AI in Software Engineering: Case Studies and Prospects"
     },
     {
       "id": "ai-software-engineering-2025",
       "title": "AI in Software Engineering: Perceived Roles and Their Impact on Adoption"
     },
     {
       "id": "ai-testing-should-2025",
       "title": "AI Testing Should Account for Sophisticated Strategic Behaviour"
     },
     {
       "id": "aiassisted-assessment-coding-2024",
       "title": "AI-Assisted Assessment of Coding Practices in Modern Code Review"
     },
     {
       "id": "aiassisted-code-editors-2025",
       "title": "AI-Assisted Code Editors with Real-Time Collaboration: A Comprehensive Review"
     },
     {
       "id": "aiassisted-fixes-code-2025",
       "title": "AI-Assisted Fixes to Code Review Comments at Scale"
     },
     {
       "id": "aiassisted-programming-decreases-2025",
       "title": "AI-Assisted Programming Decreases the Productivity of Experienced Developers by Increasing the Technical Debt and Maintenance Burden"
     },
     {
       "id": "aiaugmented-devops-paradigm-2023",
       "title": "AI-Augmented DevOps: A Paradigm Shift in Scalable Software Engineering and IT Operations"
     },
     {
       "id": "aiaugmented-software-engineering-2025",
       "title": "Towards AI-Augmented Software Engineering: A Theoretical Framework"
     },
     {
       "id": "aidriven-scholarly-peer-2025",
       "title": "AI-Driven Scholarly Peer Review via Persistent Workflow Prompting, Meta-Prompting, and Meta-Reasoning"
     },
     {
       "id": "aidriven-software-engineering-2023",
       "title": "AI-driven software engineering"
     },
     {
       "id": "aidriven-software-engineering-2024",
       "title": "AI-Driven Software Engineering – The Role of Conceptual Modeling"
     },
     {
       "id": "aiguided-modeldriven-embedded-2022",
       "title": "AI-guided Model-Driven Embedded Software Engineering"
     },
     {
       "id": "aiintegrated-software-engineering-2025",
       "title": "AI-Integrated Software Engineering: Developing Systems that Evolve with Learning Capabilities"
     },
     {
       "id": "aime-ai-system-2024",
       "title": "AIME: AI System Optimization via Multiple LLM Evaluators"
     },
     {
       "id": "ainative-software-engineering-2024",
       "title": "Towards AI-Native Software Engineering (SE 3.0): A Vision and a Challenge Roadmap"
     },
     {
       "id": "ainstein-assessing-feasibility-2025",
       "title": "AInstein: Assessing the Feasibility of AI-Generated Approaches to Research Problems"
     },
     {
       "id": "aipowered-code-review-2023",
       "title": "AI-Powered Code Review Enhancing Software Quality with Intelligent Agents"
     },
     {
       "id": "aipowered-code-review-2024",
       "title": "AI-powered Code Review with LLMs: Early Results"
     },
     {
       "id": "aipowered-peer-review-2023",
       "title": "AI-powered peer review process: An approach to enhance computer science students' engagement with code review in industry-based subjects"
     },
     {
       "id": "aipowered-software-development-2025-2",
       "title": "AI-Powered Software Development Life Cycle: From Requirements to Maintenance"
     },
     {
       "id": "aipowered-solutions-computer-2025",
       "title": "AI-Powered Solutions in Computer Science: A Comprehensive COPRAS Evaluation"
     },
     {
       "id": "ais-environmental-cost-2025",
       "title": "AI's Environmental Cost: Comparing Resource Consumption Between SLMs and LLMs Across Queries"
     },
     {
       "id": "aitutoring-software-engineering-2024",
       "title": "AI-Tutoring in Software Engineering Education: Experiences with Large Language Models in Programming Assessments"
     },
     {
       "id": "aixamine-simplified-llm-2025",
       "title": "aiXamine: Simplified LLM Safety and Security"
     },
     {
       "id": "aladdin-joint-placement-2024",
       "title": "Aladdin: Joint Placement and Scaling for SLO-Aware LLM Serving"
     },
     {
       "id": "aligned-query-expansion-2025",
       "title": "Aligned Query Expansion: Efficient Query Expansion for Information Retrieval through LLM Alignment"
     },
     {
       "id": "aligning-objective-llmbased-2024",
       "title": "Aligning the Objective of LLM-based Program Repair"
     },
     {
       "id": "alignment-faking-2024",
       "title": "Alignment Faking in Large Language Models"
     },
     {
       "id": "alignment-safety-llm-survey-2025",
       "title": "Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges"
     },
     {
       "id": "alignpro-principled-approach-2025",
       "title": "Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment"
     },
     {
       "id": "alleviating-fear-losing-2025",
       "title": "Alleviating the Fear of Losing Alignment in LLM Fine-tuning"
     },
     {
       "id": "alphacode-competition-level-2022",
       "title": "Competition-Level Code Generation with AlphaCode"
     },
     {
       "id": "alphapo-reward-shape-2025",
       "title": "AlphaPO: Reward Shape Matters for LLM Alignment"
     },
     {
       "id": "ambigswe-interactive-agents-2025",
       "title": "Ambig-SWE: Interactive Agents to Overcome Underspecificity in Software Engineering"
     },
     {
       "id": "among-us-measuring-2026",
       "title": "Among Us: Measuring and Mitigating Malicious Contributions in Model Collaboration Systems"
     },
     {
       "id": "among-us-sandbox-2025",
       "title": "Among Us: A Sandbox for Measuring and Detecting Agentic Deception"
     },
     {
       "id": "analysis-evaluation-synthetic-2025",
       "title": "Analysis and Evaluation of Synthetic Data Generation in Speech Dysfluency Detection"
     },
     {
       "id": "analysis-research-status-2025",
       "title": "Analysis of Research Status in the Field of Automated Program Repair"
     },
     {
       "id": "analysis-studentllm-interaction-2025",
       "title": "Analysis of Student-LLM Interaction in a Software Engineering Project"
     },
     {
       "id": "anatomy-capability-emergence-2026",
       "title": "Anatomy of Capability Emergence: Scale-Invariant Representation Collapse and Top-Down Reorganization in Neural Networks"
     },
     {
       "id": "ancoder-anchored-code-2026",
       "title": "AnCoder: Anchored Code Generation via Discrete Diffusion Models"
     },
     {
       "id": "animagents-coordinating-multistage-2025",
       "title": "AnimAgents: Coordinating Multi-Stage Animation Pre-Production with Human–Multi-Agent Collaboration"
     },
     {
       "id": "annotation-alignment-comparing-2024",
       "title": "Annotation alignment: Comparing LLM and human annotations of conversational safety"
     },
     {
       "id": "antiregulatory-ai-how-2025",
       "title": "Anti-Regulatory AI: How \"AI Safety\" is Leveraged Against Regulatory Oversight"
     },
     {
       "id": "appatch-automated-adaptive-2024",
       "title": "APPATCH: Automated Adaptive Prompting Large Language Models for Real-World Software Vulnerability Patching"
     },
     {
       "id": "applying-rlaif-code-2024",
       "title": "Applying RLAIF for Code Generation with API-usage in Lightweight LLMs"
     },
     {
       "id": "appworld-controllable-world-2024",
       "title": "AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents"
     },
     {
       "id": "apr-llm-survey-2025",
       "title": "A Survey of LLM-based Software Repair: Taxonomies, Design Paradigms, and Applications"
     },
     {
       "id": "april-api-synthesis-2025",
       "title": "APRIL: API Synthesis with Automatic Prompt Optimization and Reinforcement Learning"
     },
     {
       "id": "aptserve-adaptive-request-2025",
       "title": "Apt-Serve: Adaptive Request Scheduling on Hybrid Cache for Scalable LLM Inference Serving"
     },
     {
       "id": "aquallm-evaluating-accuracy-2025",
       "title": "AQUA-LLM: Evaluating Accuracy, Quantization, and Adversarial Robustness Trade-offs in LLMs for Cybersecurity Question Answering"
     },
     {
       "id": "arc-measure-intelligence-2019",
       "title": "On the Measure of Intelligence"
     },
     {
       "id": "arcmemo-abstract-reasoning-2025",
       "title": "ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory"
     },
     {
       "id": "arcs-agentic-retrievalaugmented-2025",
       "title": "ARCS: Agentic Retrieval-Augmented Code Synthesis with Iterative Refinement"
     },
     {
       "id": "arena-hard-auto-2024",
       "title": "From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline"
     },
     {
       "id": "ares-automated-evaluation-2023",
       "title": "ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems"
     },
     {
       "id": "argus-defending-against-2025",
       "title": "ARGUS: Defending Against Multimodal Indirect Prompt Injection via Steering Instruction-Following Behavior"
     },
     {
       "id": "arks-active-retrieval-2024",
       "title": "EVOR: Evolving Retrieval for Code Generation"
     },
     {
       "id": "art-adaptive-response-2025",
       "title": "ART: Adaptive Response Tuning Framework — A Multi-Agent Tournament-Based Approach to LLM Response Optimization"
     },
     {
       "id": "art-repair-optimizing-2025",
       "title": "The Art of Repair: Optimizing Iterative Program Repair with Instruction-Tuned Models"
     },
     {
       "id": "art-scaling-test-time-compute-2025",
       "title": "The Art of Scaling Test-Time Compute for Large Language Models"
     },
     {
       "id": "artifactsbench-bridging-visualinteractive-2025",
       "title": "ArtifactsBench: Bridging the Visual-Interactive Gap in LLM Code Generation Evaluation"
     },
     {
       "id": "artificial-brain-neuroscience-2026",
       "title": "The Artificial Brain: A Neuroscience Inspired Architecture for Multimodal AI Systems"
     },
     {
       "id": "artificial-human-intelligence-2025",
       "title": "Artificial or Human Intelligence?"
     },
     {
       "id": "artificial-intelligence-assistance-2026",
       "title": "Artificial intelligence assistance in foresight research: Enhancing technology assessment through data-driven methods"
     },
     {
       "id": "artificial-intelligence-health-2022",
       "title": "Artificial Intelligence for Health Message Generation: Theory, Method, and an Empirical Study Using Prompt Engineering"
     },
     {
       "id": "artificial-just-artful-2025",
       "title": "Artificial or Just Artful? Do LLMs Bend the Rules in Programming?"
     },
     {
       "id": "artificial-organisations-2026",
       "title": "Artificial Organisations"
     },
     {
       "id": "ask-me-anything-2022",
       "title": "Ask Me Anything: A Simple Strategy for Prompting Language Models"
     },
     {
       "id": "askeda-design-assistant-2024",
       "title": "Ask-EDA: A Design Assistant Empowered by LLM, Hybrid RAG and Abbreviation De-hallucination"
     },
     {
       "id": "assessing-answerability-queries-2024",
       "title": "Assessing the Answerability of Queries in Retrieval-Augmented Code Generation"
     },
     {
       "id": "assessing-correctness-llmbased-2025",
       "title": "Assessing Correctness in LLM-Based Code Generation via Uncertainty Estimation"
     },
     {
       "id": "assessing-data-extraction-2026",
       "title": "Assessing data extraction in randomized clinical trials with large language models"
     },
     {
       "id": "assessing-domainlevel-susceptibility-2026",
       "title": "Assessing Domain-Level Susceptibility to Emergent Misalignment from Narrow Finetuning"
     },
     {
       "id": "assessing-impact-code-2025",
       "title": "Assessing the Impact of Code Changes on the Fault Localizability of Large Language Models"
     },
     {
       "id": "assessing-latent-automated-2024",
       "title": "Assessing the Latent Automated Program Repair Capabilities of Large Language Models using Round-Trip Translation"
     },
     {
       "id": "assessing-verifying-task-2024",
       "title": "Assessing and Verifying Task Utility in LLM-Powered Applications"
     },
     {
       "id": "assignment-incentives-reduce-2023",
       "title": "Using Assignment Incentives to Reduce Student Procrastination and Encourage Code Review Interactions"
     },
     {
       "id": "astrovisbench-code-benchmark-2025",
       "title": "ASTROVISBENCH: A Code Benchmark for Scientific Computing and Visualization in Astronomy"
     },
     {
       "id": "asymptotic-study-incontext-2025",
       "title": "Asymptotic Study of In-Context Learning with Random Transformers Through Equivalent Models"
     },
     {
       "id": "atlas-artifact-generation-2025",
       "title": "ATLAS: Artifact Generation Through Layered Constraints and LLM × MDE Synergy"
     },
     {
       "id": "atom-thoughts-markov-2025",
       "title": "Atom of Thoughts for Markov LLM Test-Time Scaling"
     },
     {
       "id": "attacking-llms-ai-2025",
       "title": "Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models"
     },
     {
       "id": "attacks-by-content-2025",
       "title": "Attacks by Content: Automated Fact-checking is an AI Security Issue"
     },
     {
       "id": "attention-all-you-2025",
       "title": "Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs"
     },
     {
       "id": "attention-is-all-you-need-2017",
       "title": "Attention Is All You Need"
     },
     {
       "id": "attention-pruning-automated-2025",
       "title": "Attention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing"
     },
     {
       "id": "attention-tracker-detecting-2024",
       "title": "Attention Tracker: Detecting Prompt Injection Attacks in LLMs"
     },
     {
       "id": "audit-trails-accountability-2026",
       "title": "Audit Trails for Accountability in Large Language Models"
     },
     {
       "id": "auditing-fairness-under-2026",
       "title": "Auditing Fairness under Model Updates: Fundamental Complexity and Property-Preserving Updates"
     },
     {
       "id": "augmented-language-models-2023",
       "title": "Augmented Language Models: a Survey"
     },
     {
       "id": "autocodebench-large-language-2025",
       "title": "AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators"
     },
     {
       "id": "autocypher-improving-llms-2024",
       "title": "Auto-Cypher: Improving LLMs on Cypher generation via LLM-supervised generation-verification framework"
     },
     {
       "id": "autoflow-automated-workflow-2024",
       "title": "AutoFlow: Automated Workflow Generation for Large Language Model Agents"
     },
     {
       "id": "autogen-enabling-nextgen-2023",
       "title": "AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation"
     },
     {
       "id": "autogen-multi-agent-2023",
       "title": "AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation"
     },
     {
       "id": "autogenics-automated-generation-2024",
       "title": "AUTOGENICS: Automated Generation of Context-Aware Inline Comments for Code Snippets on Programming Q&A Sites Using LLM"
     },
     {
       "id": "autokaggle-multiagent-framework-2024",
       "title": "AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions"
     },
     {
       "id": "automated-bug-detection-2025",
       "title": "Automated Bug Detection and Correction in Software Development using Machine Learning"
     },
     {
       "id": "automated-cc-program-2024",
       "title": "Automated C/C++ Program Repair for High-Level Synthesis via Large Language Models"
     },
     {
       "id": "automated-code-generation-2025",
       "title": "Automated Code Generation and Validation for Software Components of Microcontrollers"
     },
     {
       "id": "automated-code-review-practice-2024",
       "title": "Automated Code Review In Practice"
     },
     {
       "id": "automated-discovery-test-2025",
       "title": "Automated Discovery of Test Oracles for Database Management Systems Using LLMs"
     },
     {
       "id": "automated-extraction-mechanical-2026",
       "title": "Automated Extraction of Mechanical Constitutive Models from Scientific Literature using Large Language Models: Applications in Cultural Heritage Conservation"
     },
     {
       "id": "automated-formalization-conceptual-2025",
       "title": "Automated Formalization via Conceptual Retrieval-Augmented LLMs"
     },
     {
       "id": "automated-knowledge-component-2025",
       "title": "Automated Knowledge Component Generation for Interpretable Knowledge Tracing in Coding Problems"
     },
     {
       "id": "automated-program-repair-2022",
       "title": "Practical Program Repair in the Era of Large Pre-trained Language Models"
     },
     {
       "id": "automated-program-repair-2023",
       "title": "Keep the Conversation Going: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT"
     },
     {
       "id": "automated-program-repair-2023-2",
       "title": "Enhancing Automated Program Repair through Fine-tuning and Prompt Engineering"
     },
     {
       "id": "automated-program-repair-2024",
       "title": "Automated Program Repair: Emerging trends pose and expose problems for benchmarks"
     },
     {
       "id": "automated-program-repair-2025",
       "title": "Automated Program Repair Based on REST API Specifications Using Large Language Models"
     },
     {
       "id": "automated-program-repair-2025-2",
       "title": "Automated Program Repair of Uncompilable Student Code"
     },
     {
       "id": "automated-repair-ai-2024",
       "title": "Automated Repair of AI Code with Large Language Models and Formal Verification"
     },
     {
       "id": "automated-repair-c-2025",
       "title": "Automated Repair of C Programs Using Large Language Models"
     },
     {
       "id": "automated-smart-contract-2025",
       "title": "Towards Automated Smart Contract Generation: Evaluation, Benchmarking, and Retrieval-Augmented Repair"
     },
     {
       "id": "automated-structural-testing-2026",
       "title": "Automated structural testing of LLM-based agents: methods, framework, and case studies"
     },
     {
       "id": "automated-test-case-2024",
       "title": "Automated Test Case Repair Using Language Models"
     },
     {
       "id": "automated-test-generation-2024",
       "title": "Automated test generation to evaluate tool-augmented LLMs as conversational AI agents"
     },
     {
       "id": "automated-unit-test-2024",
       "title": "Automated Unit Test Improvement using Large Language Models at Meta"
     },
     {
       "id": "automatic-generation-benchmarks-2024",
       "title": "Automatic Generation of Benchmarks and Reliable LLM Judgment for Code Tasks"
     },
     {
       "id": "automatic-universal-prompt-2024",
       "title": "Automatic and Universal Prompt Injection Attacks against Large Language Models"
     },
     {
       "id": "automatically-benchmarking-code-agents-2025",
       "title": "Automatically Benchmarking LLM Code Agents through Agent-driven Annotation and Evaluation"
     },
     {
       "id": "automatically-generating-web-2025",
       "title": "Automatically Generating Web Applications from Requirements Via Multi-Agent Test-Driven Development"
     },
     {
       "id": "automatically-surfacing-opportunities-2025",
       "title": "Automatically Surfacing Opportunities for Improvements In Internet-Scale Applications"
     },
     {
       "id": "automating-deception-scalable-2025",
       "title": "Automating Deception: Scalable Multi-Turn LLM Jailbreaks"
     },
     {
       "id": "automating-rest-api-2024",
       "title": "Automating REST API Postman Test Cases Using LLM"
     },
     {
       "id": "automating-structural-engineering-2025",
       "title": "Automating Structural Engineering Workflows with Large Language Model Agents"
     },
     {
       "id": "automation-ai-intergenerational-2025",
       "title": "Automation, AI, and the Intergenerational Transmission of Knowledge"
     },
     {
       "id": "autonomous-normative-multiagent-2025",
       "title": "Towards autonomous normative multi-agent systems for Human-AI software engineering teams"
     },
     {
       "id": "autonomous-supplier-evaluation-2025",
       "title": "Autonomous Supplier Evaluation and Data Stewardship with AI: Building Transparent and Resilient Supply Chains"
     },
     {
       "id": "autop2c-llmbased-agent-2025",
       "title": "AutoP2C: An LLM-Based Agent Framework for Code Repository Generation from Multimodal Content in Academic Papers"
     },
     {
       "id": "autostreampipe-llm-assisted-2025",
       "title": "AutoStreamPipe: LLM Assisted Automatic Generation of Data Stream Processing Pipelines"
     },
     {
       "id": "autotom-scaling-modelbased-2025",
       "title": "AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling"
     },
     {
       "id": "autovcoder-systematic-framework-2024",
       "title": "AutoVCoder: A Systematic Framework for Automated Verilog Code Generation using LLMs"
     },
     {
       "id": "autoverus-automated-proof-2024",
       "title": "AutoVerus: Automated Proof Generation for Rust Code"
     },
     {
       "id": "avicuna-audiovisual-llm-2024",
       "title": "Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding"
     },
     {
       "id": "awcp-workspace-delegation-2026",
       "title": "AWCP: A Workspace Delegation Protocol for Deep-Engagement Collaboration across Remote Agents"
     },
     {
       "id": "backdoor-attribution-elucidating-2025",
       "title": "Backdoor Attribution: Elucidating and Controlling Backdoors in Language Models"
     },
     {
       "id": "backdoor-samples-detection-2025",
       "title": "Backdoor Samples Detection Based on Perturbation Discrepancy Consistency in Pre-trained Language Models"
     },
     {
       "id": "backdoored-retrievers-prompt-2024",
       "title": "Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Models"
     },
     {
       "id": "backdooring-bias-large-2026",
       "title": "Backdooring Bias in Large Language Models"
     },
     {
       "id": "backdoorpowered-prompt-injection-2025",
       "title": "Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods"
     },
     {
       "id": "backportbench-multilingual-benchmark-2025",
       "title": "BackportBench: A Multilingual Benchmark for Automated Backporting of Patches"
     },
     {
       "id": "bamas-structuring-budgetaware-2025",
       "title": "BAMAS: Structuring Budget-Aware Multi-Agent Systems"
     },
     {
       "id": "bamboo-comprehensive-benchmark-2023",
       "title": "BAMBOO: A Comprehensive Benchmark for Evaluating Long Text Modeling Capacities of Large Language Models"
     },
     {
       "id": "banglaforge-llm-collaboration-2025",
       "title": "BanglaForge: LLM Collaboration with Self-Refinement for Bangla Code Generation"
     },
     {
       "id": "bashexplainer-retrievalaugmented-bash-2022",
       "title": "BASHEXPLAINER: Retrieval-Augmented Bash Code Comment Generation based on Fine-tuned CodeBERT"
     },
     {
       "id": "basics-binary-analysis-2025",
       "title": "BASICS: Binary Analysis and Stack Integrity Checker System for Buffer Overflow Mitigation"
     },
     {
       "id": "battleagentbench-benchmark-evaluating-2024",
       "title": "BattleAgentBench: A Benchmark for Evaluating Cooperation and Competition Capabilities of Language Models in Multi-Agent Systems"
     },
     {
       "id": "bayesian-reward-models-2024",
       "title": "Bayesian Reward Models for LLM Alignment"
     },
     {
       "id": "beavertails-improved-safety-2023",
       "title": "BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset"
     },
     {
       "id": "behavior-alignment-new-2024",
       "title": "Behavior Alignment: A New Perspective of Evaluating LLM-based Conversational Recommender Systems"
     },
     {
       "id": "bench-benchmark-toolagentuser-2024",
       "title": "τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains"
     },
     {
       "id": "benchmark-contamination-survey-2024",
       "title": "Benchmark Data Contamination of Large Language Models: A Survey"
     },
     {
       "id": "benchmark-expertlevel-academic-2025",
       "title": "Humanity's Last Exam"
     },
     {
       "id": "benchmark-test-time-scaling-agents-2026",
       "title": "Benchmark Test-Time Scaling of General LLM Agents"
     },
     {
       "id": "benchmarking-ai-models-2025",
       "title": "Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality"
     },
     {
       "id": "benchmarking-ai-models-2025-2",
       "title": "Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality"
     },
     {
       "id": "benchmarking-epistemology-construct-2025",
       "title": "The Benchmarking Epistemology: Construct Validity for Evaluating Machine Learning Models"
     },
     {
       "id": "benchmarking-hallucination-large-2024",
       "title": "Benchmarking Hallucination in Large Language Models based on Unanswerable Math Word Problem"
     },
     {
       "id": "benchmarking-large-language-2022",
       "title": "Benchmarking Large Language Models for Automated Verilog RTL Code Generation"
     },
     {
       "id": "benchmarking-large-language-2024",
       "title": "Benchmarking Large Language Models with Integer Sequence Generation Tasks"
     },
     {
       "id": "benchmarking-llms-unit-2025",
       "title": "Benchmarking LLMs for Unit Test Generation from Real-World Functions"
     },
     {
       "id": "benchmarks-automated-commonsense-2023",
       "title": "Benchmarks for Automated Commonsense Reasoning: A Survey"
     },
     {
       "id": "benchmarl-benchmarking-multiagent-2023",
       "title": "BenchMARL: Benchmarking Multi-Agent Reinforcement Learning"
     },
     {
       "id": "bert-pretraining-deep-2018",
       "title": "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding"
     },
     {
       "id": "best-practices-ai-2023",
       "title": "Best Practices for Using AI Tools as an Author, Peer Reviewer, or Editor"
     },
     {
       "id": "beyond-automation-job-redesign-2025",
       "title": "Beyond Automation: Redesigning Jobs with LLMs to Enhance Productivity"
     },
     {
       "id": "beyond-benchmark-innovative-2025",
       "title": "Beyond the Benchmark: Innovative Defenses Against Prompt Injection Attacks"
     },
     {
       "id": "beyond-chinchillaoptimal-accounting-2023",
       "title": "Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws"
     },
     {
       "id": "beyond-chunks-graphs-2025",
       "title": "Beyond Chunks and Graphs: Retrieval-Augmented Generation through Triplet-Driven Thinking"
     },
     {
       "id": "beyond-commit-developer-perspectives-2026",
       "title": "Beyond the Commit: Developer Perspectives on Productivity with AI Coding Assistants"
     },
     {
       "id": "beyond-correctness-benchmarking-2024",
       "title": "Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models"
     },
     {
       "id": "beyond-correctness-rewarding-2025",
       "title": "Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation"
     },
     {
       "id": "beyond-functional-correctness-2024",
       "title": "Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code"
     },
     {
       "id": "beyond-hype-comprehensive-2024",
       "title": "Beyond the Hype: A Comprehensive Review of Current Trends in Generative AI Research, Teaching Practices, and Tools"
     },
     {
       "id": "beyond-imitation-game-2022",
       "title": "Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models"
     },
     {
       "id": "beyond-mimicry-preference-2025",
       "title": "Beyond Mimicry: Testing Preference Coherence in Large Language Models Through AI-Specific Trade-Off Scenarios"
     },
     {
       "id": "beyond-promptinduced-lies-2025",
       "title": "Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts"
     },
     {
       "id": "beyond-quantity-trajectory-2026",
       "title": "Beyond Quantity: Trajectory Diversity Scaling for Code Agents"
     },
     {
       "id": "beyond-semantic-entropy-2025",
       "title": "Beyond Semantic Entropy: Boosting LLM Uncertainty Quantification with Pairwise Semantic Similarity"
     },
     {
       "id": "beyond-singleagent-safety-2025",
       "title": "Beyond Single-Agent Safety: A Taxonomy of Risks in LLM-to-LLM Interactions"
     },
     {
       "id": "beyond-static-datasets-2023",
       "title": "Beyond Static Datasets: A Deep Interaction Approach to LLM Evaluation"
     },
     {
       "id": "beyond-static-pattern-2025",
       "title": "Exploring Automatic Cryptographic API Misuse Detection in the Era of LLMs"
     },
     {
       "id": "beyond-synthetic-benchmarks-2025",
       "title": "Beyond Synthetic Benchmarks: Evaluating LLM Performance on Real-World Class-Level Code Generation"
     },
     {
       "id": "beyond-textual-context-2025",
       "title": "Beyond Textual Context: Structural Graph Encoding with Adaptive Space Alignment to alleviate the hallucination of LLMs"
     },
     {
       "id": "beyond-token-probes-2025",
       "title": "Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT"
     },
     {
       "id": "bias-assessment-mitigation-2023",
       "title": "Bias Testing and Mitigation in LLM-based Code Generation"
     },
     {
       "id": "bias-unveiled-investigating-2024",
       "title": "Bias Unveiled: Investigating Social Bias in LLM-Generated Code"
     },
     {
       "id": "biasalert-plugandplay-tool-2024",
       "title": "BiasAlert: A Plug-and-play Tool for Social Bias Detection in LLMs"
     },
     {
       "id": "bigcodebench-2024",
       "title": "BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions"
     },
     {
       "id": "bigrpo-bidirectional-optimization-2025",
       "title": "BI-GRPO: Bidirectional Optimization for Jailbreak Backdoor Injection on LLMs"
     },
     {
       "id": "bioplanner-automatic-evaluation-2023",
       "title": "BioPlanner: Automatic Evaluation of LLMs on Protocol Planning in Biology"
     },
     {
       "id": "bioragent-retrievalaugmented-generation-2024",
       "title": "BioRAGent: A Retrieval-Augmented Generation System for Showcasing Generative Query Expansion and Domain-Specific Search for Scientific Q&A"
     },
     {
       "id": "biotrouble-multiagent-workflow-2026",
       "title": "BioTrouble: A Multi-Agent Workflow for Troubleshooting Molecular Biology Techniques"
     },
     {
       "id": "bitsaicr-automated-code-2025",
       "title": "BitsAI-CR: Automated Code Review via LLM in Practice"
     },
     {
       "id": "blockdialect-blockwise-finegrained-2025",
       "title": "BlockDialect: Block-wise Fine-grained Mixed Format Quantization for Energy-Efficient LLM Inference"
     },
     {
       "id": "boosting-llm-reasoning-2025",
       "title": "Boosting LLM Reasoning via Spontaneous Self-Correction"
     },
     {
       "id": "boosting-redundancybased-automated-2023",
       "title": "Boosting Redundancy-based Automated Program Repair by Fine-grained Pattern Mining"
     },
     {
       "id": "bottomup-domainspecific-superintelligence-2025",
       "title": "Bottom-up Domain-specific Superintelligence: A Reliable Knowledge Graph is What We Need"
     },
     {
       "id": "boute-costefficient-llm-2026",
       "title": "BOUTE: Cost-Efficient LLM Serving with Heterogeneous LLMs and GPUs via Multi-Objective Bayesian Optimization"
     },
     {
       "id": "bpo-staying-close-2024",
       "title": "BPO: Staying Close to the Behavior LLM Creates Better Online LLM Alignment"
     },
     {
       "id": "break-sequential-dependency-2024",
       "title": "Break the Sequential Dependency of LLM Inference Using Lookahead Decoding"
     },
     {
       "id": "breaking-prompt-wall-2025",
       "title": "Breaking the Prompt Wall (I): A Real-World Case Study of Attacking ChatGPT via Lightweight Prompt Injection"
     },
     {
       "id": "bridging-human-interpretation-2026",
       "title": "Bridging Human Interpretation and Machine Representation: A Landscape of Qualitative Data Analysis in the LLM Era"
     },
     {
       "id": "bridging-llmgenerated-code-2025",
       "title": "Bridging LLM-Generated Code and Requirements: Reverse Generation technique and SBC Metric for Developer Insights"
     },
     {
       "id": "bridging-mde-ai-2023",
       "title": "Bridging MDE and AI: A Systematic Review of Domain-Specific Languages and Model-Driven Practices in AI Software Systems Engineering"
     },
     {
       "id": "broken-neural-scaling-2022",
       "title": "Broken Neural Scaling Laws"
     },
     {
       "id": "browserarena-web-agents-2025",
       "title": "BrowserArena: Evaluating LLM Agents on Real-World Web Navigation Tasks"
     },
     {
       "id": "browsesafe-understanding-preventing-2025",
       "title": "BrowseSafe: Understanding and Preventing Prompt Injection Within AI Browser Agents"
     },
     {
       "id": "budgetaware-agentic-routing-2026",
       "title": "Budget-Aware Agentic Routing via Boundary-Guided Training"
     },
     {
       "id": "bugdar-aiaugmented-secure-2025",
       "title": "Bugdar: AI-Augmented Secure Code Review for GitHub Pull Requests"
     },
     {
       "id": "bugs-large-language-2024",
       "title": "Bugs in Large Language Models Generated Code: An Empirical Study"
     },
     {
       "id": "bugsphp-dataset-automated-2024",
       "title": "BugsPHP: A dataset for Automated Program Repair in PHP"
     },
     {
       "id": "build-your-personalized-2025",
       "title": "Build Your Personalized Research Group: A Multiagent Framework for Continual and Interactive Science Automation"
     },
     {
       "id": "building-coding-assistant-2024",
       "title": "Building A Coding Assistant via the Retrieval-Augmented Language Model"
     },
     {
       "id": "building-cooperative-embodied-2023",
       "title": "Building Cooperative Embodied Agents Modularly with Large Language Models"
     },
     {
       "id": "building-understandable-messaging-2024",
       "title": "Building Understandable Messaging for Policy and Evidence Review (BUMPER) with AI"
     },
     {
       "id": "bypassing-llm-guardrails-2025",
       "title": "Bypassing LLM Guardrails: An Empirical Analysis of Evasion Attacks against Prompt Injection and Jailbreak Detection Systems"
     },
     {
       "id": "bytesized32refactored-extensible-interactive-2025",
       "title": "ByteSized32Refactored: Towards an Extensible Interactive Text Games Corpus for LLM World Modeling and Evaluation"
     },
     {
       "id": "c3po-optimized-large-2025",
       "title": "C3PO: Optimized Large Language Model Cascades with Probabilistic Cost Constraints for Reasoning"
     },
     {
       "id": "cacheprune-neuralbased-attribution-2025",
       "title": "CachePrune: Neural-Based Attribution Defense Against Indirect Prompt Injection Attacks"
     },
     {
       "id": "calibrating-llm-judges-2025",
       "title": "Calibrating LLM Judges: Linear Probes for Fast and Reliable Uncertainty Estimation"
     },
     {
       "id": "calibration-large-language-2026",
       "title": "On Calibration of Large Language Models: From Response To Capability"
     },
     {
       "id": "camel-communicative-agents-2023",
       "title": "CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society"
     },
     {
       "id": "can-1b-llm-2025",
       "title": "Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling"
     },
     {
       "id": "can-ai-serve-2023",
       "title": "Can AI Serve as a Substitute for Human Subjects in Software Engineering Research?"
     },
     {
       "id": "can-chatgpt-support-2024",
       "title": "Can ChatGPT Support Developers? An Empirical Evaluation of Large Language Models for Code Generation"
     },
     {
       "id": "can-indirect-prompt-2025",
       "title": "Can Indirect Prompt Injection Attacks Be Detected and Removed?"
     },
     {
       "id": "can-large-language-2025",
       "title": "Can Large Language Models Develop Gambling Addiction?"
     },
     {
       "id": "can-llm-replace-2023",
       "title": "Can LLM Replace Stack Overflow? A Study on Robustness and Reliability of Large Language Model Code Generation"
     },
     {
       "id": "can-llms-replace-2025",
       "title": "Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering"
     },
     {
       "id": "can-reasoning-models-2025",
       "title": "Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability"
     },
     {
       "id": "can-vibe-coding-2025",
       "title": "Can Vibe Coding Beat Graduate CS Students? An LLM vs. Human Coding Tournament on Market-driven Strategic Planning"
     },
     {
       "id": "can-we-automatically-2022",
       "title": "Can We Automatically Fix Bugs by Learning Edit Operations?"
     },
     {
       "id": "canaries-coal-mine-2025",
       "title": "Canaries in the Coal Mine? Six Facts about the Recent Employment Effects of Artificial Intelligence"
     },
     {
       "id": "capability-ceilings-autoregressive-2025",
       "title": "Capability Ceilings in Autoregressive Language Models: Empirical Evidence from Knowledge-Intensive Tasks"
     },
     {
       "id": "capabilityoriented-training-induced-2026",
       "title": "Capability-Oriented Training Induced Alignment Risk"
     },
     {
       "id": "capture-contextaware-prompt-2025",
       "title": "CAPTURE: Context-Aware Prompt Injection Testing and Robustness Enhancement"
     },
     {
       "id": "carbon-footprint-evaluation-2025",
       "title": "Carbon Footprint Evaluation of Code Generation through LLM as a Service"
     },
     {
       "id": "caredio-cultural-alignment-2025",
       "title": "CAReDiO: Cultural Alignment of LLM via Representativeness and Distinctiveness Guided Data Optimization"
     },
     {
       "id": "case-4bit-precision-2022",
       "title": "The case for 4-bit precision: k-bit Inference Scaling Laws"
     },
     {
       "id": "case-learned-cloud-2025",
       "title": "A Case for Learned Cloud Emulators"
     },
     {
       "id": "case-study-transformative-2025",
       "title": "A case study on the transformative potential of AI in software engineering on LeetCode and ChatGPT"
     },
     {
       "id": "cast-enhancing-code-2025",
       "title": "CAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree"
     },
     {
       "id": "caster-breaking-costperformance-2026",
       "title": "CASTER: Breaking the Cost-Performance Barrier in Multi-Agent Orchestration via Context-Aware Strategy for Task Efficient Routing"
     },
     {
       "id": "catarena-evaluating-evolutionary-2025",
       "title": "CATArena: Evaluating Evolutionary Capabilities of Code Agents via Iterative Tournaments"
     },
     {
       "id": "catch-me-if-2025",
       "title": "Catch Me If You Can: Rogue AI Detection and Correction at Scale"
     },
     {
       "id": "catdb-datacatalogguided-llmbased-2025",
       "title": "CatDB: Data-catalog-guided, LLM-based Generation of Data-centric ML Pipelines"
     },
     {
       "id": "causalarmor-efficient-indirect-2026",
       "title": "CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution"
     },
     {
       "id": "cbfllm-safe-control-2024",
       "title": "CBF-LLM: Safe Control for LLM Alignment"
     },
     {
       "id": "ccfc-core-corefullcore-2025",
       "title": "CCFC: Core & Core–Full–Core Dual-Track Defense for LLM Jailbreak Protection"
     },
     {
       "id": "cctest-testing-repairing-2022",
       "title": "CCTEST: Testing and Repairing Code Completion Systems"
     },
     {
       "id": "chain-of-thought-prompting-2022",
       "title": "Chain-of-Thought Prompting Elicits Reasoning in Large Language Models"
     },
     {
       "id": "chainofthought-prompting-obscures-2025",
       "title": "Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical Evaluation"
     },
     {
       "id": "chainpoll-high-efficacy-2023",
       "title": "ChainPoll: A High Efficacy Method for LLM Hallucination Detection"
     },
     {
       "id": "challenge-optimization-context-2025",
       "title": "Challenge on Optimization of Context Collection for Code Completion"
     },
     {
       "id": "challenges-humanagent-communication-2024",
       "title": "Challenges in Human-Agent Communication"
     },
     {
       "id": "challenges-paths-ai-2025",
       "title": "Challenges and Paths Towards AI for Software Engineering"
     },
     {
       "id": "changes-coding-behavior-2026",
       "title": "Changes in Coding Behavior and Performance Since the Introduction of LLMs"
     },
     {
       "id": "chaos-engineering-20-2025",
       "title": "Chaos Engineering 2.0: A Review of AI-Driven, Policy-Guided Resilience for Multi-Cloud Systems"
     },
     {
       "id": "characterizing-llm-inference-2025",
       "title": "Characterizing LLM Inference Energy-Performance Tradeoffs across Workloads and GPU Scaling"
     },
     {
       "id": "chasing-progress-not-2024",
       "title": "Chasing Progress, Not Perfection: Revisiting Strategies for End-to-End LLM Plan Generation"
     },
     {
       "id": "chat-bankmanfried-exploration-2024",
       "title": "Chat Bankman-Fried: an Exploration of LLM Alignment in Finance"
     },
     {
       "id": "chatassert-llmbased-test-2025",
       "title": "CHATASSERT: LLM-Based Test Oracle Generation With External Tools Assistance"
     },
     {
       "id": "chatbot-arena-open-2024",
       "title": "Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference"
     },
     {
       "id": "chatdev-communicative-agents-2023",
       "title": "ChatDev: Communicative Agents for Software Development"
     },
     {
       "id": "chateval-better-llmbased-2023",
       "title": "ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate"
     },
     {
       "id": "chatgpt-agent-system-2025",
       "title": "ChatGPT Agent System Card"
     },
     {
       "id": "chatgpt-not-all-2023",
       "title": "ChatGPT is not all you need. A State of the Art Review of large Generative AI models"
     },
     {
       "id": "chatinject-abusing-chat-2025",
       "title": "ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents"
     },
     {
       "id": "chatofthought-collaborative-multiagent-2025",
       "title": "Chat-of-Thought: Collaborative Multi-Agent System for Generating Domain Specific Information"
     },
     {
       "id": "chatunitest-framework-llmbased-2023",
       "title": "ChatUniTest: A Framework for LLM-Based Test Generation"
     },
     {
       "id": "check-your-facts-2023",
       "title": "Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback"
     },
     {
       "id": "checkpointgcg-auditing-attacking-2025",
       "title": "Checkpoint-GCG: Auditing and Attacking Fine-Tuning-Based Prompt Injection Defenses"
     },
     {
       "id": "chinchilla-compute-optimal-2022",
       "title": "Training Compute-Optimal Large Language Models"
     },
     {
       "id": "chipbench-nextstep-benchmark-2026",
       "title": "ChipBench: A Next-Step Benchmark for Evaluating LLM Performance in AI-Aided Chip Design"
     },
     {
       "id": "chopchop-programmable-framework-2025",
       "title": "ChopChop: A Programmable Framework for Semantically Constraining the Output of Language Models"
     },
     {
       "id": "chorus-zeroshot-hierarchical-2025",
       "title": "CHORUS: Zero-shot Hierarchical Retrieval and Orchestration for Generating Linear Programming Code"
     },
     {
       "id": "ciata-risk-assessment-2025",
       "title": "CIA+TA Risk Assessment for AI Reasoning Vulnerabilities"
     },
     {
       "id": "cigar-costefficient-program-2024",
       "title": "CigaR: Cost-efficient Program Repair with LLMs"
     },
     {
       "id": "citationenhanced-generation-llmbased-2024",
       "title": "Citation-Enhanced Generation for LLM-based Chatbots"
     },
     {
       "id": "citationgrounded-code-comprehension-2025",
       "title": "Citation-Grounded Code Comprehension: Preventing LLM Hallucination Through Hybrid Retrieval and Graph-Augmented Context"
     },
     {
       "id": "citywalk-enhancing-llmbased-2025",
       "title": "CITYWALK: Enhancing LLM-Based C++ Unit Test Generation via Project-Dependency Awareness and Language-Specific Knowledge"
     },
     {
       "id": "ckgfuzzer-llmbased-fuzz-2025",
       "title": "CKGFuzzer: LLM-Based Fuzz Driver Generation Enhanced By Code Knowledge Graph"
     },
     {
       "id": "clarifygpt-empowering-llmbased-2023",
       "title": "ClarifyGPT: Empowering LLM-based Code Generation with Intention Clarification"
     },
     {
       "id": "clarifygpt-framework-enhancing-2024",
       "title": "ClarifyGPT: Empowering LLM-based Code Generation with Intention Clarification"
     },
     {
       "id": "classeval-manuallycrafted-benchmark-2023",
       "title": "ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation"
     },
     {
       "id": "classifying-addressing-diversity-2025",
       "title": "Classifying and Addressing the Diversity of Errors in Retrieval-Augmented Generation Systems"
     },
     {
       "id": "classit-conversational-lecturealigned-2025",
       "title": "CLASS-IT: Conversational and Lecture-Aligned Small-Scale Instruction Tuning for BabyLMs"
     },
     {
       "id": "claude-sonnet-45-2025",
       "title": "System Card: Claude Sonnet 4.5"
     },
     {
       "id": "clinnoteagents-llm-multiagent-2025",
       "title": "ClinNoteAgents: An LLM Multi-Agent System for Predicting and Interpreting Heart Failure 30-Day Readmission from Clinical Notes"
     },
     {
       "id": "cloud-platforms-developing-2024",
       "title": "Cloud Platforms for Developing Generative AI Solutions: A Scoping Review of Tools and Services"
     },
     {
       "id": "cloudevalyaml-practical-benchmark-2023",
       "title": "CloudEval-YAML: A Practical Benchmark for Cloud Configuration Generation"
     },
     {
       "id": "cloudfix-automated-policy-2025",
       "title": "CloudFix: Automated Policy Repair for Cloud Access Control Policies Using Large Language Models"
     },
     {
       "id": "cmoe-converting-mixtureofexperts-2025",
       "title": "CMoE: Converting Mixture-of-Experts from Dense to Accelerate LLM Inference"
     },
     {
       "id": "cocomic-code-completion-2022",
       "title": "COCOMIC: Code Completion By Jointly Modeling In-file and Cross-file Context"
     },
     {
       "id": "cocreating-automated-mhealth-2023",
       "title": "Cocreating an Automated mHealth Apps Systematic Review Process With Generative AI: Design Science Research Approach"
     },
     {
       "id": "codamosa-escaping-coverage-2023",
       "title": "CODAMOSA: Escaping Coverage Plateaus in Test Generation with Pre-trained Large Language Models"
     },
     {
       "id": "code-aesthetics-agentic-2025",
       "title": "Code Aesthetics with Agentic Reward Feedback"
     },
     {
       "id": "code-hallucination-2024",
       "title": "Code Hallucination"
     },
     {
       "id": "code-hallucinations-slr-2025",
       "title": "A Systematic Literature Review of Code Hallucinations in LLMs: Characterization, Mitigation Methods, Challenges, and Future Directions for Reliable AI"
     },
     {
       "id": "code-less-align-2024",
       "title": "Code Less, Align More: Efficient LLM Fine-tuning for Code Generation with Data Pruning"
     },
     {
       "id": "code-llama-2023",
       "title": "Code Llama: Open Foundation Models for Code"
     },
     {
       "id": "code-me-me-2025",
       "title": "Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows"
     },
     {
       "id": "code-ownership-opensource-2023",
       "title": "Code Ownership in Open-Source AI Software Security"
     },
     {
       "id": "code-review-automation-2025",
       "title": "Code Review Automation using Retrieval Augmented Generation"
     },
     {
       "id": "code-review-survey-pre-post-llm-2026",
       "title": "A Survey of Code Review Benchmarks and Evaluation Practices in Pre-LLM and LLM Era"
     },
     {
       "id": "codearena-collective-evaluation-2025",
       "title": "CodeArena: A Collective Evaluation Platform for LLM Code Generation"
     },
     {
       "id": "codeaware-prompting-study-2024",
       "title": "Code-Aware Prompting: A Study of Coverage-Guided Test Generation in Regression Setting using LLM"
     },
     {
       "id": "codebenchgen-creating-scalable-2024",
       "title": "CodeBenchGen: Creating Scalable Execution-Based Code Generation Benchmarks"
     },
     {
       "id": "codebert-pretrained-model-2020",
       "title": "CodeBERT: A Pre-Trained Model for Programming and Natural Languages"
     },
     {
       "id": "codecontests-highquality-test-2025",
       "title": "CodeContests+: High-Quality Test Case Generation for Competitive Programming"
     },
     {
       "id": "codecor-llmbased-selfreflective-2025",
       "title": "CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generation"
     },
     {
       "id": "codecriticbench-holistic-code-2025",
       "title": "CodeCriticBench: A Holistic Code Critique Benchmark for Large Language Models"
     },
     {
       "id": "codediting-reasoningbased-metric-2025",
       "title": "CODE-DITING: A Reasoning-Based Metric for Functional Alignment in Code Evaluation"
     },
     {
       "id": "codeelo-benchmarking-competitionlevel-2025",
       "title": "CODEELO: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings"
     },
     {
       "id": "codefill-multitoken-code-2022",
       "title": "CodeFill: Multi-token Code Completion by Jointly Learning from Structure and Naming Sequences"
     },
     {
       "id": "codegrag-bridging-gap-2024",
       "title": "CodeGRAG: Bridging the Gap between Natural Language and Programming Language via Graphical Retrieval Augmented Generation"
     },
     {
       "id": "codeinsight-curated-dataset-2024",
       "title": "CodeInsight: A Curated Dataset of Practical Coding Solutions from Stack Overflow"
     },
     {
       "id": "codejudge-evaluating-code-2024",
       "title": "CodeJudge: Evaluating Code Generation with Large Language Models"
     },
     {
       "id": "codejudgebench-benchmarking-llmasajudge-2025",
       "title": "CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks"
     },
     {
       "id": "codemark-imperceptible-watermarking-2023",
       "title": "CodeMark: Imperceptible Watermarking for Code Datasets against Neural Code Completion Models"
     },
     {
       "id": "codemirage-hallucinations-code-2024",
       "title": "CodeMirage: Hallucinations in Code Generated by Large Language Models"
     },
     {
       "id": "codemmlu-multitask-benchmark-2024",
       "title": "CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMs"
     },
     {
       "id": "codemmlu-multitask-benchmark-2024-2",
       "title": "CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMs"
     },
     {
       "id": "codemorph-mitigating-data-2025",
       "title": "CODEMORPH: Mitigating Data Leakage in Large Language Model Assessment"
     },
     {
       "id": "codepde-inference-framework-2025",
       "title": "CodePDE: An Inference Framework for LLM-driven PDE Solver Generation"
     },
     {
       "id": "codepromptzip-codespecific-prompt-2025",
       "title": "CODEPROMPTZIP: Code-specific Prompt Compression for Retrieval-Augmented Generation in Coding Tasks with LMs"
     },
     {
       "id": "coderagbench-can-retrieval-2024",
       "title": "CODERAG-BENCH: Can Retrieval Augment Code Generation?"
     },
     {
       "id": "codereviewqa-code-review-2025",
       "title": "CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models"
     },
     {
       "id": "coderl-improving-code-2025",
       "title": "CODERL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment"
     },
     {
       "id": "codescope-executionbased-multilingual-2023",
       "title": "CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation"
     },
     {
       "id": "codescore-evaluating-code-2023",
       "title": "CodeScore: Evaluating Code Generation by Learning Code Execution"
     },
     {
       "id": "codesift-llmbased-referenceless-2024",
       "title": "CodeSift: An LLM-Based Reference-Less Framework for Automatic Code Validation"
     },
     {
       "id": "codetm4-detecting-machinegenerated-2025",
       "title": "CoDet-M4: Detecting Machine-Generated Code in Multi-Lingual, Multi-Generator and Multi-Domain Settings"
     },
     {
       "id": "codex-humaneval-2021",
       "title": "Evaluating Large Language Models Trained on Code"
     },
     {
       "id": "codexity-secure-aiassisted-2024",
       "title": "Codexity: Secure AI-assisted Code Generation"
     },
     {
       "id": "codified-context-infrastructure-2026",
       "title": "Codified Context: Infrastructure for AI Agents in a Complex Codebase"
     },
     {
       "id": "coding-agents-generating-2026",
       "title": "Are Coding Agents Generating Over-Mocked Tests? An Empirical Study"
     },
     {
       "id": "coevolving-llm-coder-2025",
       "title": "Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning"
     },
     {
       "id": "coffe-code-efficiency-2025",
       "title": "COFFE: A Code Efficiency Benchmark for Code Generation"
     },
     {
       "id": "cognitive-control-architecture-2025",
       "title": "Cognitive Control Architecture (CCA): A Lifecycle Supervision Framework for Robustly Aligned AI Agents"
     },
     {
       "id": "cognitive-models-ai-2026",
       "title": "Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents"
     },
     {
       "id": "cognitive-overload-attackprompt-2024",
       "title": "Cognitive Overload Attack: Prompt Injection for Long Context"
     },
     {
       "id": "coladder-supporting-programmers-2023",
       "title": "CoLadder: Supporting Programmers with Hierarchical Code Generation in Multi-Level Abstraction"
     },
     {
       "id": "collab-controlled-decoding-2025",
       "title": "Collab: Controlled Decoding using Mixture of Agents for LLM Alignment"
     },
     {
       "id": "collaborating-genai-incentives-2025",
       "title": "Collaborating with GenAI: Incentives and Replacements"
     },
     {
       "id": "collaboration-all-you-2025",
       "title": "Collaboration is all you need: LLM Assisted Safe Code Translation"
     },
     {
       "id": "collaborative-agents-automated-2025",
       "title": "Collaborative Agents for Automated Program Repair in Ruby"
     },
     {
       "id": "collubench-benchmark-predicting-2024",
       "title": "Collu-Bench: A Benchmark for Predicting Language Model Hallucinations in Code"
     },
     {
       "id": "colm-collaborative-large-2025",
       "title": "CoLM: Collaborative Large Models via A Client-Server Paradigm"
     },
     {
       "id": "colt-lightweight-multillm-2026",
       "title": "COLT: Lightweight Multi-LLM Collaboration through Shared MCTS Reasoning for Model Compilation"
     },
     {
       "id": "comback-versatile-dataset-2024",
       "title": "ComBack: A Versatile Dataset for Enhancing Compiler Backend Development Efficiency"
     },
     {
       "id": "combined-approach-program-2024",
       "title": "A Combined Approach of Program Analysis and Deep Learning for Code Completion"
     },
     {
       "id": "combining-costconstrained-runtime-2025",
       "title": "Combining Cost-Constrained Runtime Monitors for AI Safety"
     },
     {
       "id": "combining-large-language-2025",
       "title": "Combining Large Language Models with Static Analyzers for Code Review Generation"
     },
     {
       "id": "comparative-analysis-pretrained-2025",
       "title": "Comparative Analysis of Pre-trained Code Language Models for Automated Program Repair via Code Infill Generation"
     },
     {
       "id": "comparative-review-ai-2024",
       "title": "A Comparative Review of AI Techniques for Automated Code Generation in Software Development: Advancements, Challenges, and Future Directions"
     },
     {
       "id": "comparative-study-ai-2025",
       "title": "A Comparative Study of AI and Human Evaluation for Student Website Projects"
     },
     {
       "id": "comparative-study-dsl-2024",
       "title": "A Comparative Study of DSL Code Generation: Fine-Tuning vs. Optimized Retrieval Augmentation"
     },
     {
       "id": "comparative-study-large-2025",
       "title": "A comparative study of large language models with chain-of-thought prompting for automated program repair"
     },
     {
       "id": "comparing-codefree-bespoke-2024",
       "title": "Comparing code-free and bespoke deep learning approaches in ophthalmology"
     },
     {
       "id": "compass-contrastive-learning-2026",
       "title": "ComPass: Contrastive Learning for Automated Patch Correctness Assessment in Program Repair"
     },
     {
       "id": "competitive-programming-reasoning-models-2025",
       "title": "Competitive Programming with Large Reasoning Models"
     },
     {
       "id": "compilable-neural-code-2022",
       "title": "Compilable Neural Code Generation with Compiler Feedback"
     },
     {
       "id": "compilation-quotient-cq-2024",
       "title": "Compilation Quotient (CQ): A Metric for the Compilation Hardness of Programming Languages"
     },
     {
       "id": "compiler-feedback-loops-2025",
       "title": "Feedback Loops and Code Perturbations in LLM-based Software Engineering: A Case Study on a C-to-Rust Translation System"
     },
     {
       "id": "compilernext-searchbased-compiler-2025",
       "title": "Compiler.next: A Search-Based Compiler to Power the AI-Native Future of Software Engineering"
     },
     {
       "id": "completion-by-comprehension-2025",
       "title": "Completion by Comprehension: Guiding Code Generation with Multi-Granularity Understanding"
     },
     {
       "id": "complexcodeeval-benchmark-evaluating-2024",
       "title": "ComplexCodeEval: A Benchmark for Evaluating Large Code Models on More Complex Code"
     },
     {
       "id": "compounding-reliability-2025",
       "title": "The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs"
     },
     {
       "id": "comprehensive-analysis-machine-2025",
       "title": "Comprehensive Analysis of Machine Learning and Deep Learning models on Prompt Injection Classification using Natural Language Processing techniques"
     },
     {
       "id": "comprehensive-llm-secure-code-2025",
       "title": "Rethinking the Evaluation of Secure Code Generation"
     },
     {
       "id": "comprehensive-study-posttraining-2023",
       "title": "ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation"
     },
     {
       "id": "comprehensive-survey-aidriven-2024",
       "title": "A Comprehensive Survey of AI-Driven Advancements and Techniques in Automated Program Repair and Code Generation"
     },
     {
       "id": "comprehensive-survey-llm-2024",
       "title": "A Comprehensive Survey of LLM Alignment Techniques: RLHF, RLAIF, PPO, DPO and More"
     },
     {
       "id": "comprehensive-survey-trustworthiness-2025",
       "title": "A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models"
     },
     {
       "id": "comprehensive-taxonomy-hallucinations-2025",
       "title": "A comprehensive taxonomy of hallucinations in Large Language Models"
     },
     {
       "id": "comprehensive-verilog-design-2025",
       "title": "Comprehensive Verilog Design Problems: A Next-Generation Benchmark Dataset for Evaluating Large Language Models and Agents on RTL Design and Verification"
     },
     {
       "id": "compute-optimal-inference-2024",
       "title": "Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters"
     },
     {
       "id": "concept-influence-leveraging-2026",
       "title": "Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution"
     },
     {
       "id": "conceptguard-neurosymbolic-safety-2025",
       "title": "ConceptGuard: Neuro-Symbolic Safety Guardrails via Sparse Interpretable Jailbreak Concepts"
     },
     {
       "id": "concerned-data-contamination-2024",
       "title": "Concerned with Data Contamination? Assessing Countermeasures in Code Language Model"
     },
     {
       "id": "conco-optimizing-compilation-2025",
       "title": "ConCo: Optimizing Compilation of Concurrent Tensor Programs on Shared GPU"
     },
     {
       "id": "concordance-randomised-controlled-2024",
       "title": "Concordance of randomised controlled trials for artificial intelligence interventions with the CONSORT-AI reporting guidelines"
     },
     {
       "id": "concrete-roadmap-safety-2025",
       "title": "A Concrete Roadmap towards Safety Cases based on Chain-of-Thought Monitoring"
     },
     {
       "id": "condor-enhance-llm-2025",
       "title": "Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement"
     },
     {
       "id": "confidencedriven-multiscale-model-2026",
       "title": "Confidence-Driven Multi-Scale Model Selection for Cost-Efficient Inference"
     },
     {
       "id": "confidenceguided-stepwise-model-2025",
       "title": "Confidence-Guided Stepwise Model Routing for Cost-Efficient Reasoning"
     },
     {
       "id": "configuring-agentic-coding-tools-2026",
       "title": "Configuring Agentic AI Coding Tools: An Exploratory Study"
     },
     {
       "id": "conformal-constrained-policy-2025",
       "title": "Conformal Constrained Policy Optimization for Cost-Effective LLM Agents"
     },
     {
       "id": "consistency-key-detecting-2025",
       "title": "Consistency Is the Key: Detecting Hallucinations in LLM Generated Text By Checking Inconsistencies About Key Facts"
     },
     {
       "id": "constitutional-ai-2022",
       "title": "Constitutional AI: Harmlessness from AI Feedback"
     },
     {
       "id": "constrained-decoding-diffusion-2025",
       "title": "Constrained Decoding of Diffusion LLMs with Context-Free Grammars"
     },
     {
       "id": "constrained-decoding-fillinthemiddle-2024",
       "title": "Constrained Decoding for Fill-in-the-Middle Code Language Models via Efficient Left and Right Quotienting of Context-Sensitive Grammars"
     },
     {
       "id": "context-composing-full-2024",
       "title": "Context Composing for Full Line Code Completion"
     },
     {
       "id": "context-engineering-ai-2025",
       "title": "Context Engineering for AI Agents in Open-Source Software"
     },
     {
       "id": "contextalignment-activating-enhancing-2025",
       "title": "Context-Alignment: Activating and Enhancing LLM Capabilities in Time Series"
     },
     {
       "id": "contextaugmented-code-generation-2024",
       "title": "Context-Augmented Code Generation Using Programming Knowledge Graphs"
     },
     {
       "id": "continuous-software-engineering-2024",
       "title": "Continuous Software Engineering Practices in AI/ML Development Past the Narrow Lens of MLOps: Adoption Challenges"
     },
     {
       "id": "contrastrepair-enhancing-conversationbased-2024",
       "title": "ContrastRepair: Enhancing Conversation-Based Automated Program Repair via Contrastive Test Case Pairs"
     },
     {
       "id": "control-models-inide-2026",
       "title": "Control Models for In-IDE Code Completion: Saving Inference Costs While Improving Completion Quality Metrics"
     },
     {
       "id": "controlled-selfevolution-algorithmic-2026",
       "title": "Controlled Self-Evolution for Algorithmic Code Optimization"
     },
     {
       "id": "convergence-dynamics-agenttoagent-2025",
       "title": "Convergence Dynamics of Agent-to-Agent Interactions with Misaligned Objectives"
     },
     {
       "id": "cooperbench-why-coding-2026",
       "title": "CooperBench: Why Coding Agents Cannot be Your Teammates Yet"
     },
     {
       "id": "copilot-arena-platform-2025",
       "title": "Copilot Arena: A Platform for Code LLM Evaluation in the Wild"
     },
     {
       "id": "copilot-code-quality-empirical-2023",
       "title": "Evaluating the Code Quality of AI-Assisted Code Generation Tools: An Empirical Study on GitHub Copilot, Amazon CodeWhisperer, and ChatGPT"
     },
     {
       "id": "copilot-efficiency-real-world-2024",
       "title": "Transforming Software Development: Evaluating the Efficiency and Challenges of GitHub Copilot in Real-World Projects"
     },
     {
       "id": "copilot-evaluation-harness-2024",
       "title": "Copilot Evaluation Harness: Evaluating LLM-Guided Software Programming"
     },
     {
       "id": "copilot-longitudinal-case-study-2025",
       "title": "Developer Productivity With and Without GitHub Copilot: A Longitudinal Mixed-Methods Case Study"
     },
     {
       "id": "copilot-productivity-controlled-2023",
       "title": "The Impact of AI on Developer Productivity: Evidence from GitHub Copilot"
     },
     {
       "id": "copilot-security-weaknesses-2023",
       "title": "Security Weaknesses of Copilot-Generated Code in GitHub Projects: An Empirical Study"
     },
     {
       "id": "copilot-zoominfo-productivity-2025",
       "title": "Experience with GitHub Copilot for Developer Productivity at Zoominfo"
     },
     {
       "id": "copiloting-copilots-fusing-2023",
       "title": "Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair"
     },
     {
       "id": "coprompter-usercentric-evaluation-2024",
       "title": "CoPrompter: User-Centric Evaluation of LLM Instruction Alignment for Improved Prompt Engineering"
     },
     {
       "id": "core-bench-computational-2024",
       "title": "CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark"
     },
     {
       "id": "core-comprehensive-ontological-2026",
       "title": "CORE: Comprehensive Ontological Relation Evaluation for Large Language Models"
     },
     {
       "id": "corecodebench-decoupling-code-2025",
       "title": "CORECODEBENCH: Decoupling Code Intelligence via Fine-Grained Repository-Level Tasks"
     },
     {
       "id": "correctnessguaranteed-code-generation-2025",
       "title": "Correctness-Guaranteed Code Generation via Constrained Decoding"
     },
     {
       "id": "cosight-enhancing-llmbased-2025",
       "title": "Co-Sight: Enhancing LLM-Based Agents via Conflict-Aware Meta-Verification and Trustworthy Reasoning with Structured Facts"
     },
     {
       "id": "cost-accuracy-longterm-2026",
       "title": "Cost and accuracy of long-term memory in Distributed Multi-Agent Systems based on Large Language Models"
     },
     {
       "id": "cost-dynamic-reasoning-2025",
       "title": "The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective"
     },
     {
       "id": "cotbased-synthesizer-enhancing-2025",
       "title": "CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis"
     },
     {
       "id": "cotdeceptoradversarial-code-obfuscation-2025",
       "title": "CoTDeceptor: Adversarial Code Obfuscation Against CoT-Enhanced LLM Code Agents"
     },
     {
       "id": "cotrag-integrating-chain-2025",
       "title": "CoT-RAG: Integrating Chain of Thought and Retrieval-Augmented Generation to Enhance Reasoning in Large Language Models"
     },
     {
       "id": "cotran-llmbased-code-2023",
       "title": "CoTran: An LLM-based Code Translator using Reinforcement Learning with Feedback from Compiler and Symbolic Execution"
     },
     {
       "id": "courtguard-local-multiagent-2025",
       "title": "CourtGuard: A Local, Multiagent Prompt Injection Classifier"
     },
     {
       "id": "coverup-effective-high-2024",
       "title": "CoverUp: Effective High Coverage Test Generation for Python"
     },
     {
       "id": "cracking-code-hallucination-2024",
       "title": "Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence"
     },
     {
       "id": "cracking-code-scoping-2024",
       "title": "Cracking the code: a scoping review to unite disciplines in tackling legal issues in health artificial intelligence"
     },
     {
       "id": "cracking-sql-barriers-2025",
       "title": "Cracking SQL Barriers: An LLM-based Dialect Translation System"
     },
     {
       "id": "creativeval-evaluating-creativity-2024",
       "title": "CreativEval: Evaluating Creativity of LLM-Based Hardware Code Generation"
     },
     {
       "id": "critical-evaluation-defenses-2025",
       "title": "A Critical Evaluation of Defenses against Prompt Injection Attacks"
     },
     {
       "id": "critical-review-large-2023",
       "title": "A Critical Review of Large Language Model on Software Engineering: An Example from ChatGPT and Automated Program Repair"
     },
     {
       "id": "crosscodeeval-diverse-multilingual-2023",
       "title": "CROSSCODEEVAL: A Diverse and Multilingual Benchmark for Cross-File Code Completion"
     },
     {
       "id": "crossllm-generalization-behavioral-2025",
       "title": "Cross-LLM Generalization of Behavioral Backdoor Detection in AI Agent Supply Chains"
     },
     {
       "id": "crossmodal-memory-compression-2026",
       "title": "Cross-Modal Memory Compression for Efficient Multi-Agent Debate"
     },
     {
       "id": "crossplatform-evaluation-large-2025",
       "title": "Cross-Platform Evaluation of Large Language Model Safety in Pediatric Consultations: Evolution of Adversarial Robustness and the Scale Paradox"
     },
     {
       "id": "crqbench-benchmark-code-2024",
       "title": "CRQBench: A Benchmark of Code Reasoning Questions"
     },
     {
       "id": "crscore-reinforcement-learning-2025",
       "title": "CRScore++: Reinforcement Learning with Verifiable Tool and AI Feedback for Code Review"
     },
     {
       "id": "cruxeval-benchmark-code-2024",
       "title": "CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution"
     },
     {
       "id": "cruxevalx-benchmark-multilingual-2024",
       "title": "CRUXEVAL-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution"
     },
     {
       "id": "crystalyse-multitool-agent-2025",
       "title": "Crystalyse: a multi-tool agent for materials design"
     },
     {
       "id": "cuckoo-attack-stealthy-2025",
       "title": "Cuckoo Attack: Stealthy and Persistent Attacks Against AI-IDE"
     },
     {
       "id": "cudaforge-agent-framework-2025",
       "title": "CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization"
     },
     {
       "id": "cumo-scaling-multimodal-2024",
       "title": "CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts"
     },
     {
       "id": "curious-critical-thinker-2025",
       "title": "Curious, Critical Thinker, Empathetic, and Ethically Responsible: Essential Soft Skills for Data Scientists in Software Engineering"
     },
     {
       "id": "current-challenges-software-2024",
       "title": "The Current Challenges of Software Engineering in the Era of Large Language Models"
     },
     {
       "id": "curriculum-guided-massive-2025",
       "title": "Curriculum Guided Massive Multi Agent System Solving for Robust Long Horizon Tasks"
     },
     {
       "id": "cweval-outcomedriven-evaluation-2025",
       "title": "CWEVAL: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation"
     },
     {
       "id": "cyberbot-ontologygrounded-retrieval-2025",
       "title": "CyberBOT: Towards Reliable Cybersecurity Education via Ontology-Grounded Retrieval Augmented Generation"
     },
     {
       "id": "cyberphysical-system-defense-2025",
       "title": "Cyber-Physical System Defense Against Structured False Data Injection Attacks Using an Adaptive Security Framework with Passivity Enhancement"
     },
     {
       "id": "cybersecurity-ai-hacking-2025",
       "title": "Cybersecurity AI: Hacking the AI Hackers via Prompt Injection"
     },
     {
       "id": "dacode-agent-data-2024",
       "title": "DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models"
     },
     {
       "id": "dancing-critiques-enhancing-2025",
       "title": "Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique"
     },
     {
       "id": "dangers-poisoned-llms-2025",
       "title": "On The Dangers of Poisoned LLMs In Security Automation"
     },
     {
       "id": "dapo-opensource-llm-2025",
       "title": "DAPO: An Open-Source LLM Reinforcement Learning System at Scale"
     },
     {
       "id": "deep-rl-matters-2018",
       "title": "Deep Reinforcement Learning that Matters"
     },
     {
       "id": "gans-created-equal-2018",
       "title": "Are GANs Created Equal? A Large-Scale Study"
     },
     {
       "id": "leakage-reproducibility-crisis-2023",
       "title": "Leakage and the Reproducibility Crisis in ML-based Science"
     },
     {
       "id": "lost-middle-how-2023",
       "title": "Lost in the Middle: How Language Models Use Long Contexts"
     },
     {
       "id": "lost-mix-evaluating-2025",
       "title": "Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text"
     },
     {
       "id": "lpcd-unified-framework-2025",
       "title": "LPCD: Unified Framework from Layer-Wise to Submodule Quantization"
     },
     {
       "id": "lutllm-efficient-large-2025",
       "title": "LUT-LLM: Efficient Large Language Model Inference with Memory-based Computations on FPGAs"
     },
     {
       "id": "lynx-open-source-2024",
       "title": "Lynx: An Open Source Hallucination Evaluation Model"
     },
     {
       "id": "mactg-multiagent-collaborative-2024",
       "title": "MaCTG: Multi-Agent Collaborative Thought Graph for Automatic Programming"
     },
     {
       "id": "madspear-conformitydriven-prompt-2025",
       "title": "MAD-SPEAR: A Conformity-Driven Prompt Injection Attack on Multi-Agent Debate Systems"
     },
     {
       "id": "maestro-multiagent-evaluation-2026",
       "title": "MAESTRO: Multi-Agent Evaluation Suite for Testing, Reliability, and Observability"
     },
     {
       "id": "magentic-marketplace-opensource-2025",
       "title": "Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets"
     },
     {
       "id": "magenticone-generalist-multiagent-2024",
       "title": "Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks"
     },
     {
       "id": "neurips-reproducibility-2021",
       "title": "Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)"
     },
     {
       "id": "questionable-practices-ml-2024",
       "title": "Questionable practices in machine learning"
     },
     {
       "id": "reforms-consensus-ml-2024",
       "title": "Determination of the force transmission error in a single-sinker magnetic suspension densimeter due to the fluid-specific effect and its correction for use with gas mixtures containing oxygen"
     },
     {
       "id": "reproducibility-ml-overview-2025",
       "title": "Reproducibility in Machine Learning-based Research: Overview, Barriers and Drivers"
     },
     {
       "id": "show-your-work-2019",
       "title": "Show Your Work: Improved Reporting of Experimental Results"
     },
     {
       "id": "troubling-trends-ml-2018",
       "title": "Troubling Trends in Machine Learning Scholarship"
     },
     {
       "id": "trust-ai-benchmarks-2025",
       "title": "Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation"
     },
     {
       "id": "wakefield-ileal-lymphoid-1998",
       "title": "Ileal-lymphoid-nodular hyperplasia, non-specific colitis, and pervasive developmental disorder in children"
     }
   ],
   "edges": [
     {
       "source": "2025-ai-agent-2026",
       "target": "remote-labor-index-2025"
     },
     {
       "source": "3dshape2vecset-3d-shape-2023",
       "target": "attention-is-all-you-need-2017"
     },
     {
       "source": "3dshape2vecset-3d-shape-2023",
       "target": "bert-pretraining-deep-2018"
     },
     {
       "source": "3dshape2vecset-3d-shape-2023",
       "target": "diffusionsdf-conditional-generative-2022"
     },
     {
       "source": "a2hcoder-llmdriven-coding-2025",
       "target": "chatdev-communicative-agents-2023"
     },
     {
       "source": "a2hcoder-llmdriven-coding-2025",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "a2hcoder-llmdriven-coding-2025",
       "target": "verimind-agentic-llm-2025"
     },
     {
       "source": "a2hcoder-llmdriven-coding-2025",
       "target": "chateval-better-llmbased-2023"
     },
     {
       "source": "a2hcoder-llmdriven-coding-2025",
       "target": "generative-agents-interactive-2023"
     },
     {
       "source": "a2hcoder-llmdriven-coding-2025",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "aart-aiassisted-redteaming-2023",
       "target": "constitutional-ai-2022"
     },
     {
       "source": "aart-aiassisted-redteaming-2023",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "aart-aiassisted-redteaming-2023",
       "target": "selfconsistency-improves-chain-2022"
     },
     {
       "source": "aart-aiassisted-redteaming-2023",
       "target": "self-instruct-aligning-language-2022"
     },
     {
       "source": "acar-adaptive-complexity-2026",
       "target": "scaffolded-model-capability-2023"
     },
     {
       "source": "acar-adaptive-complexity-2026",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "accelerating-automatic-program-2025",
       "target": "rapgen-retrievalaugmented-patch-2023"
     },
     {
       "source": "accelerating-automatic-program-2025",
       "target": "code-llama-2023"
     },
     {
       "source": "accelerating-automatic-program-2025",
       "target": "starcoder2-2024"
     },
     {
       "source": "accelerating-automatic-program-2025",
       "target": "empirical-study-finetuning-2023"
     },
     {
       "source": "accelerating-automatic-program-2025",
       "target": "agentless-2024"
     },
     {
       "source": "accelerating-automatic-program-2025",
       "target": "impact-code-language-2023"
     },
     {
       "source": "accelerating-automatic-program-2025",
       "target": "repairllama-efficient-representations-2023"
     },
     {
       "source": "accelerating-large-language-2023",
       "target": "fast-inference-from-2022"
     },
     {
       "source": "accelerating-large-language-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "accelerating-large-language-2023",
       "target": "chinchilla-compute-optimal-2022"
     },
     {
       "source": "across-programming-language-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "across-programming-language-2025",
       "target": "code-llama-2023"
     },
     {
       "source": "across-programming-language-2025",
       "target": "coderagbench-can-retrieval-2024"
     },
     {
       "source": "across-programming-language-2025",
       "target": "deepseek-coder-2024"
     },
     {
       "source": "across-programming-language-2025",
       "target": "qwen25coder-technical-report-2024"
     },
     {
       "source": "across-programming-language-2025",
       "target": "multiple-scalable-polyglot-2023"
     },
     {
       "source": "across-programming-language-2025",
       "target": "empirical-study-retrievalaugmented-2025"
     },
     {
       "source": "across-programming-language-2025",
       "target": "how-should-i-2025"
     },
     {
       "source": "across-programming-language-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "adafuse-adaptive-ensemble-2026",
       "target": "llama-3-herd-2024"
     },
     {
       "source": "adafuse-adaptive-ensemble-2026",
       "target": "selfconsistency-improves-chain-2022"
     },
     {
       "source": "adafuse-adaptive-ensemble-2026",
       "target": "scaffolded-model-capability-2023"
     },
     {
       "source": "adafuse-adaptive-ensemble-2026",
       "target": "tree-thoughts-deliberate-2023"
     },
     {
       "source": "adaplanner-adaptive-planning-2023",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "adaplanner-adaptive-planning-2023",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "adaplanner-adaptive-planning-2023",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "adaptevolve-improving-efficiency-2026",
       "target": "livecodebench-2024"
     },
     {
       "source": "adaptevolve-improving-efficiency-2026",
       "target": "scaffolded-model-capability-2023"
     },
     {
       "source": "adaptevolve-improving-efficiency-2026",
       "target": "selfconsistency-improves-chain-2022"
     },
     {
       "source": "adapting-knowledge-prompt-2025",
       "target": "automated-program-repair-2022"
     },
     {
       "source": "adapting-knowledge-prompt-2025",
       "target": "impact-code-language-2023"
     },
     {
       "source": "adapting-knowledge-prompt-2025",
       "target": "empirical-study-finetuning-2023"
     },
     {
       "source": "adapting-knowledge-prompt-2025",
       "target": "rapgen-retrievalaugmented-patch-2023"
     },
     {
       "source": "adapting-knowledge-prompt-2025",
       "target": "how-effective-neural-2023"
     },
     {
       "source": "adaptive-attacks-break-2025",
       "target": "agentdojo-dynamic-environment-2024"
     },
     {
       "source": "adaptive-attacks-break-2025",
       "target": "jatmo-prompt-injection-2023"
     },
     {
       "source": "adaptive-attacks-break-2025",
       "target": "not-what-youve-2023"
     },
     {
       "source": "adaptive-attacks-break-2025",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "adaptive-attacks-bypass-defenses-2025",
       "target": "agentdojo-dynamic-environment-2024"
     },
     {
       "source": "adaptive-attacks-bypass-defenses-2025",
       "target": "not-what-youve-2023"
     },
     {
       "source": "adaptive-attacks-bypass-defenses-2025",
       "target": "jailbreaking-safety-aligned-llms-2024"
     },
     {
       "source": "adaptive-attacks-bypass-defenses-2025",
       "target": "datasentinel-gametheoretic-detection-2025"
     },
     {
       "source": "adaptive-attacks-bypass-defenses-2025",
       "target": "melon-provable-defense-2025"
     },
     {
       "source": "adaptive-test-generation-2023",
       "target": "codamosa-escaping-coverage-2023"
     },
     {
       "source": "adaptive-test-generation-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "adaptrack-constrained-decoding-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "adaptrack-constrained-decoding-2025",
       "target": "monitorguided-decoding-code-2023"
     },
     {
       "source": "adaptrack-constrained-decoding-2025",
       "target": "copiloting-copilots-fusing-2023"
     },
     {
       "source": "adaptrack-constrained-decoding-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "adaptrack-constrained-decoding-2025",
       "target": "deepseek-coder-2024"
     },
     {
       "source": "adas-automated-design-2024",
       "target": "swe-bench-2023"
     },
     {
       "source": "adas-automated-design-2024",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "adas-automated-design-2024",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "adas-automated-design-2024",
       "target": "ai-scientist-fully-2024"
     },
     {
       "source": "adas-automated-design-2024",
       "target": "improving-factuality-reasoning-2023"
     },
     {
       "source": "adas-automated-design-2024",
       "target": "voyager-open-ended-2023"
     },
     {
       "source": "adoption-generative-artificial-2026",
       "target": "metr-rct-2025"
     },
     {
       "source": "adoption-generative-artificial-2026",
       "target": "copilot-productivity-controlled-2023"
     },
     {
       "source": "adoption-generative-artificial-2026",
       "target": "navigating-complexity-generative-2023"
     },
     {
       "source": "advancements-generative-ai-2023",
       "target": "attention-is-all-you-need-2017"
     },
     {
       "source": "advancements-generative-ai-2023",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "advancements-generative-ai-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "advancements-generative-ai-2023",
       "target": "alphacode-competition-level-2022"
     },
     {
       "source": "advancing-code-generation-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "advancing-code-generation-2025",
       "target": "your-code-generated-2023"
     },
     {
       "source": "advancing-code-generation-2025",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "advancing-code-generation-2025",
       "target": "chatdev-communicative-agents-2023"
     },
     {
       "source": "advancing-code-generation-2025",
       "target": "survey-llm-code-generation-2025"
     },
     {
       "source": "advancing-code-generation-2025",
       "target": "rise-potential-large-2023"
     },
     {
       "source": "advancing-code-generation-2025",
       "target": "clarifygpt-empowering-llmbased-2023"
     },
     {
       "source": "advancing-language-model-2025",
       "target": "compute-optimal-inference-2024"
     },
     {
       "source": "advancing-language-model-2025",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "advancing-language-model-2025",
       "target": "qwen25-technical-report-2024"
     },
     {
       "source": "advancing-language-model-2025",
       "target": "gpqa-graduatelevel-googleproof-2023"
     },
     {
       "source": "advancing-largemolecule-discovery-2025",
       "target": "attention-is-all-you-need-2017"
     },
     {
       "source": "advancing-methodological-development-2025",
       "target": "emergent-abilities-large-2022"
     },
     {
       "source": "advancing-methodological-development-2025",
       "target": "emergent-abilities-mirage-2023"
     },
     {
       "source": "advancing-nursing-regulation-2025",
       "target": "metr-rct-2025"
     },
     {
       "source": "advancing-software-quality-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "advancing-software-quality-2025",
       "target": "test-driven-interactive-code-gen-2024"
     },
     {
       "source": "advancing-software-quality-2025",
       "target": "aipowered-code-review-2024"
     },
     {
       "source": "advancing-software-quality-2025",
       "target": "llmassisted-static-analysis-2024"
     },
     {
       "source": "adversarial-bug-reports-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "adversarial-bug-reports-2025",
       "target": "swe-agent-2024"
     },
     {
       "source": "adversarial-bug-reports-2025",
       "target": "repairagent-llm-bug-repair-2024"
     },
     {
       "source": "adversarial-bug-reports-2025",
       "target": "openhands-ai-sw-agent-2024"
     },
     {
       "source": "adversarial-bug-reports-2025",
       "target": "not-what-youve-2023"
     },
     {
       "source": "adversarial-threat-vectors-2025",
       "target": "attention-is-all-you-need-2017"
     },
     {
       "source": "advevomarl-shaping-internalized-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "advevomarl-shaping-internalized-2025",
       "target": "gpqa-graduatelevel-googleproof-2023"
     },
     {
       "source": "advevomarl-shaping-internalized-2025",
       "target": "evomarl-coevolutionary-multiagent-2025"
     },
     {
       "source": "aegis-automated-coevolutionary-2025",
       "target": "defending-against-indirect-2024"
     },
     {
       "source": "aegis-automated-coevolutionary-2025",
       "target": "promptarmor-simple-yet-2025"
     },
     {
       "source": "aegis20-diverse-ai-2025",
       "target": "beavertails-improved-safety-2023"
     },
     {
       "source": "aegis20-diverse-ai-2025",
       "target": "aart-aiassisted-redteaming-2023"
     },
     {
       "source": "aegisagent-autonomous-defense-2025",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "aegisagent-autonomous-defense-2025",
       "target": "selfconsistency-improves-chain-2022"
     },
     {
       "source": "aegisagent-autonomous-defense-2025",
       "target": "prompt-injection-llm-apps-2023"
     },
     {
       "source": "aegisagent-autonomous-defense-2025",
       "target": "gemma-open-models-2024"
     },
     {
       "source": "agent-contracts-formal-2026",
       "target": "uc-berkeley-mast-2025"
     },
     {
       "source": "agent-contracts-formal-2026",
       "target": "livecodebench-2024"
     },
     {
       "source": "agent-contracts-formal-2026",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "agent-contracts-formal-2026",
       "target": "autogen-multi-agent-2023"
     },
     {
       "source": "agent-contracts-formal-2026",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "agent-contracts-formal-2026",
       "target": "multi-agent-collaboration-survey-2025"
     },
     {
       "source": "agent-developer-practices-2025",
       "target": "uc-berkeley-mast-2025"
     },
     {
       "source": "agent-developer-practices-2025",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "agent-developer-practices-2025",
       "target": "agentless-2024"
     },
     {
       "source": "agent-developer-practices-2025",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "agent-error-taxonomy-2025",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "agent-error-taxonomy-2025",
       "target": "tree-thoughts-deliberate-2023"
     },
     {
       "source": "agent-error-taxonomy-2025",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "agent-error-taxonomy-2025",
       "target": "gaia-benchmark-general-2023"
     },
     {
       "source": "agent-error-taxonomy-2025",
       "target": "uc-berkeley-mast-2025"
     },
     {
       "source": "agent-error-taxonomy-2025",
       "target": "which-agent-causes-2025"
     },
     {
       "source": "agent-error-taxonomy-2025",
       "target": "toolllm-facilitating-large-2023"
     },
     {
       "source": "agent-security-bench-2024",
       "target": "agentdojo-dynamic-environment-2024"
     },
     {
       "source": "agent-security-bench-2024",
       "target": "formalizing-benchmarking-prompt-2023"
     },
     {
       "source": "agent-security-bench-2024",
       "target": "not-what-youve-2023"
     },
     {
       "source": "agent-security-bench-2024",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "agent-security-bench-2024",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "agentasajudge-evaluate-agents-2024",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "agentasajudge-evaluate-agents-2024",
       "target": "swe-bench-2023"
     },
     {
       "source": "agentasajudge-evaluate-agents-2024",
       "target": "openhands-ai-sw-agent-2024"
     },
     {
       "source": "agentasajudge-evaluate-agents-2024",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "agentasajudge-evaluate-agents-2024",
       "target": "mlebench-evaluating-machine-2024"
     },
     {
       "source": "agentasajudge-evaluate-agents-2024",
       "target": "swe-agent-2024"
     },
     {
       "source": "agentasajudge-evaluate-agents-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "agentasajudge-evaluate-agents-2024",
       "target": "chateval-better-llmbased-2023"
     },
     {
       "source": "agentasajudge-evaluate-agents-2024",
       "target": "agentless-2024"
     },
     {
       "source": "agentask-multiagent-systems-2025",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "agentask-multiagent-systems-2025",
       "target": "chatdev-communicative-agents-2023"
     },
     {
       "source": "agentask-multiagent-systems-2025",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "agentask-multiagent-systems-2025",
       "target": "agentbench-evaluating-llms-2023"
     },
     {
       "source": "agentask-multiagent-systems-2025",
       "target": "which-agent-causes-2025"
     },
     {
       "source": "agentask-multiagent-systems-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "agentbased-evaluation-framework-2025",
       "target": "codejudge-evaluating-code-2024"
     },
     {
       "source": "agentbased-evaluation-framework-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "agentbased-evaluation-framework-2025",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "agentbased-evaluation-framework-2025",
       "target": "rise-potential-large-2023"
     },
     {
       "source": "agentbased-evaluation-framework-2025",
       "target": "llm-agents-se-survey-2024"
     },
     {
       "source": "agentbased-evaluation-framework-2025",
       "target": "chatdev-communicative-agents-2023"
     },
     {
       "source": "agentbased-evaluation-framework-2025",
       "target": "can-llms-replace-2025"
     },
     {
       "source": "agentbench-evaluating-llms-2023",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "agentbench-evaluating-llms-2023",
       "target": "mind2web-generalist-agent-2023"
     },
     {
       "source": "agentbench-evaluating-llms-2023",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "agentbench-evaluating-llms-2023",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "agentbench-evaluating-llms-2023",
       "target": "generative-agents-interactive-2023"
     },
     {
       "source": "agentbench-evaluating-llms-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "agentbench-evaluating-llms-2023",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "agentbench-evaluating-llms-2023",
       "target": "autogen-multi-agent-2023"
     },
     {
       "source": "agentdojo-dynamic-environment-2024",
       "target": "agentbench-evaluating-llms-2023"
     },
     {
       "source": "agentdojo-dynamic-environment-2024",
       "target": "webarena-autonomous-agents-2023"
     },
     {
       "source": "agentdojo-dynamic-environment-2024",
       "target": "not-what-youve-2023"
     },
     {
       "source": "agentdojo-dynamic-environment-2024",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "agentdojo-dynamic-environment-2024",
       "target": "defending-against-indirect-2024"
     },
     {
       "source": "agentfuzzer-generic-blackbox-2025",
       "target": "agentdojo-dynamic-environment-2024"
     },
     {
       "source": "agentfuzzer-generic-blackbox-2025",
       "target": "formalizing-benchmarking-prompt-2023"
     },
     {
       "source": "agentfuzzer-generic-blackbox-2025",
       "target": "defending-against-indirect-2024"
     },
     {
       "source": "agentfuzzer-generic-blackbox-2025",
       "target": "webarena-autonomous-agents-2023"
     },
     {
       "source": "agentic-adoption-github-2026",
       "target": "metr-rct-2025"
     },
     {
       "source": "agentic-adoption-github-2026",
       "target": "swe-bench-2023"
     },
     {
       "source": "agentic-adoption-github-2026",
       "target": "cursor-speed-quality-tradeoff-2025"
     },
     {
       "source": "agentic-adoption-github-2026",
       "target": "understanding-software-engineering-2025"
     },
     {
       "source": "agentic-adoption-github-2026",
       "target": "copilot-productivity-controlled-2023"
     },
     {
       "source": "agentic-adoption-github-2026",
       "target": "context-engineering-ai-2025"
     },
     {
       "source": "agentic-adoption-github-2026",
       "target": "agentless-2024"
     },
     {
       "source": "agentic-adoption-github-2026",
       "target": "promises-perils-timely-2026"
     },
     {
       "source": "agentic-adoption-github-2026",
       "target": "measuring-ai-ability-2025"
     },
     {
       "source": "agentic-ai-architectures-2026",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "agentic-ai-architectures-2026",
       "target": "swe-agent-2024"
     },
     {
       "source": "agentic-ai-architectures-2026",
       "target": "survey-autonomous-llm-agents-2023"
     },
     {
       "source": "agentic-ai-architectures-2026",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "agentic-ai-architectures-2026",
       "target": "voyager-open-ended-2023"
     },
     {
       "source": "agentic-ai-architectures-2026",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "agentic-ai-architectures-2026",
       "target": "tree-thoughts-deliberate-2023"
     },
     {
       "source": "agentic-ai-architectures-2026",
       "target": "autogen-enabling-nextgen-2023"
     },
     {
       "source": "agentic-ai-architectures-2026",
       "target": "osworld-benchmarking-multimodal-2024"
     },
     {
       "source": "agentic-ai-architectures-2026",
       "target": "gaia-benchmark-general-2023"
     },
     {
       "source": "agentic-ai-architectures-2026",
       "target": "formalizing-benchmarking-prompt-2023"
     },
     {
       "source": "agentic-ai-architectures-2026",
       "target": "agentbench-evaluating-llms-2023"
     },
     {
       "source": "agentic-ai-assessment-framework-2025",
       "target": "uc-berkeley-mast-2025"
     },
     {
       "source": "agentic-ai-assessment-framework-2025",
       "target": "which-agent-causes-2025"
     },
     {
       "source": "agentic-ai-assessment-framework-2025",
       "target": "llm-long-term-memory-eval-2024"
     },
     {
       "source": "agentic-ai-modernization-2026",
       "target": "autogen-multi-agent-2023"
     },
     {
       "source": "agentic-ai-modernization-2026",
       "target": "agentmesh-cooperative-multiagent-2025"
     },
     {
       "source": "agentic-ai-modernization-2026",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "agentic-ai-modernization-2026",
       "target": "survey-code-gen-llm-agents-2025"
     },
     {
       "source": "agentic-ai-security-survey-2025",
       "target": "agentdojo-dynamic-environment-2024"
     },
     {
       "source": "agentic-ai-security-survey-2025",
       "target": "webarena-autonomous-agents-2023"
     },
     {
       "source": "agentic-ai-security-survey-2025",
       "target": "adaptive-attacks-break-2025"
     },
     {
       "source": "agentic-ai-security-survey-2025",
       "target": "not-what-youve-2023"
     },
     {
       "source": "agentic-ai-security-survey-2025",
       "target": "bench-benchmark-toolagentuser-2024"
     },
     {
       "source": "agentic-ai-security-survey-2025",
       "target": "osworld-benchmarking-multimodal-2024"
     },
     {
       "source": "agentic-ai-software-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "agentic-ai-software-2025",
       "target": "swe-agent-2024"
     },
     {
       "source": "agentic-ai-software-2025",
       "target": "openhands-ai-sw-agent-2024"
     },
     {
       "source": "agentic-ai-software-2025",
       "target": "repoaudit-autonomous-llmagent-2025"
     },
     {
       "source": "agentic-ai-software-2025-2",
       "target": "repairagent-llm-bug-repair-2024"
     },
     {
       "source": "agentic-ai-software-2025-2",
       "target": "swelancer-can-frontier-2025"
     },
     {
       "source": "agentic-ai-software-2025-2",
       "target": "codeaware-prompting-study-2024"
     },
     {
       "source": "agentic-ai-software-2025-2",
       "target": "swe-agent-2024"
     },
     {
       "source": "agentic-bug-reproduction-2025",
       "target": "swtbench-testing-validating-2024"
     },
     {
       "source": "agentic-bug-reproduction-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "agentic-bug-reproduction-2025",
       "target": "swe-agent-2024"
     },
     {
       "source": "agentic-bug-reproduction-2025",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "agentic-bug-reproduction-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "agentic-bug-reproduction-2025",
       "target": "llms-se-systematic-review-2023"
     },
     {
       "source": "agentic-programming-survey-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "agentic-programming-survey-2025",
       "target": "swe-agent-2024"
     },
     {
       "source": "agentic-programming-survey-2025",
       "target": "chatdev-communicative-agents-2023"
     },
     {
       "source": "agentic-programming-survey-2025",
       "target": "llms-se-systematic-review-2023"
     },
     {
       "source": "agentic-programming-survey-2025",
       "target": "llm-agents-se-survey-2024"
     },
     {
       "source": "agentic-programming-survey-2025",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "agentic-programming-survey-2025",
       "target": "voyager-open-ended-2023"
     },
     {
       "source": "agentic-programming-survey-2025",
       "target": "openhands-ai-sw-agent-2024"
     },
     {
       "source": "agentic-programming-survey-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "agentic-programming-survey-2025",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "agentic-refactoring-empirical-2025",
       "target": "rise-ai-teammates-2025"
     },
     {
       "source": "agentic-software-engineering-2025",
       "target": "software-engineering-by-2025"
     },
     {
       "source": "agentic-software-engineering-2025",
       "target": "llms-se-systematic-review-2023"
     },
     {
       "source": "agentic-software-engineering-2025",
       "target": "rise-ai-teammates-2025"
     },
     {
       "source": "agentic-software-engineering-2025",
       "target": "agentic-ai-software-2025-2"
     },
     {
       "source": "agentic-software-engineering-2025",
       "target": "agentic-programming-survey-2025"
     },
     {
       "source": "agentless-2024",
       "target": "swe-bench-2023"
     },
     {
       "source": "agentless-2024",
       "target": "swe-agent-2024"
     },
     {
       "source": "agentless-2024",
       "target": "llm-agents-se-survey-2024"
     },
     {
       "source": "agentless-2024",
       "target": "masai-modular-architecture-2024"
     },
     {
       "source": "agentless-2024",
       "target": "automated-program-repair-2022"
     },
     {
       "source": "agentless-2024",
       "target": "systematic-literature-review-2024"
     },
     {
       "source": "agentless-2024",
       "target": "rise-potential-large-2023"
     },
     {
       "source": "agentmesh-cooperative-multiagent-2025",
       "target": "chatdev-communicative-agents-2023"
     },
     {
       "source": "agents-of-chaos-2026",
       "target": "not-what-youve-2023"
     },
     {
       "source": "agents-of-chaos-2026",
       "target": "frontier-models-in-context-scheming-2024"
     },
     {
       "source": "agents4plc-automating-closedloop-2024",
       "target": "chatdev-communicative-agents-2023"
     },
     {
       "source": "agents4plc-automating-closedloop-2024",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "agents4plc-automating-closedloop-2024",
       "target": "mapcoder-multiagent-code-2024"
     },
     {
       "source": "agents4plc-automating-closedloop-2024",
       "target": "autogen-enabling-nextgen-2023"
     },
     {
       "source": "agents4plc-automating-closedloop-2024",
       "target": "llm-agents-se-survey-2024"
     },
     {
       "source": "agents4plc-automating-closedloop-2024",
       "target": "code-llama-2023"
     },
     {
       "source": "agents4plc-automating-closedloop-2024",
       "target": "automated-program-repair-2023"
     },
     {
       "source": "agents4plc-automating-closedloop-2024",
       "target": "survey-autonomous-llm-agents-2023"
     },
     {
       "source": "agents4plc-automating-closedloop-2024",
       "target": "llms-se-systematic-review-2023"
     },
     {
       "source": "agentsllm-augmentative-generation-2025",
       "target": "chatbot-arena-open-2024"
     },
     {
       "source": "agentsllm-augmentative-generation-2025",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "agentsllm-augmentative-generation-2025",
       "target": "autogen-multi-agent-2023"
     },
     {
       "source": "agentsllm-augmentative-generation-2025",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "agentsllm-augmentative-generation-2025",
       "target": "toolformer-language-models-2023"
     },
     {
       "source": "agentsnet-coordination-collaborative-2025",
       "target": "agentbench-evaluating-llms-2023"
     },
     {
       "source": "agentsnet-coordination-collaborative-2025",
       "target": "llmcoordination-evaluating-analyzing-2023"
     },
     {
       "source": "agentsnet-coordination-collaborative-2025",
       "target": "improving-factuality-reasoning-2023"
     },
     {
       "source": "agentsnet-coordination-collaborative-2025",
       "target": "emergent-abilities-mirage-2023"
     },
     {
       "source": "agentsnet-coordination-collaborative-2025",
       "target": "generative-agents-interactive-2023"
     },
     {
       "source": "agentsnet-coordination-collaborative-2025",
       "target": "bench-benchmark-toolagentuser-2024"
     },
     {
       "source": "agentspawn-adaptive-multiagent-2026",
       "target": "survey-code-gen-llm-agents-2025"
     },
     {
       "source": "agentspawn-adaptive-multiagent-2026",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "agentspawn-adaptive-multiagent-2026",
       "target": "chatdev-communicative-agents-2023"
     },
     {
       "source": "agentspawn-adaptive-multiagent-2026",
       "target": "memgpt-llms-as-2023"
     },
     {
       "source": "agentspawn-adaptive-multiagent-2026",
       "target": "multi-agent-collaboration-survey-2025"
     },
     {
       "source": "agentspawn-adaptive-multiagent-2026",
       "target": "plan-and-act-long-horizon-2025"
     },
     {
       "source": "agentspawn-adaptive-multiagent-2026",
       "target": "agentic-programming-survey-2025"
     },
     {
       "source": "agentspawn-adaptive-multiagent-2026",
       "target": "when-singleagent-skills-2026"
     },
     {
       "source": "agenttypo-adaptive-typographic-2025",
       "target": "visualwebarena-evaluating-multimodal-2024"
     },
     {
       "source": "agenttypo-adaptive-typographic-2025",
       "target": "not-what-youve-2023"
     },
     {
       "source": "agentvigil-generic-blackbox-2025",
       "target": "agentdojo-dynamic-environment-2024"
     },
     {
       "source": "agentvigil-generic-blackbox-2025",
       "target": "not-what-youve-2023"
     },
     {
       "source": "agentvigil-generic-blackbox-2025",
       "target": "formalizing-benchmarking-prompt-2023"
     },
     {
       "source": "agentvigil-generic-blackbox-2025",
       "target": "defending-against-indirect-2024"
     },
     {
       "source": "agentvigil-generic-blackbox-2025",
       "target": "webarena-autonomous-agents-2023"
     },
     {
       "source": "agentvigil-generic-blackbox-2025",
       "target": "visualwebarena-evaluating-multimodal-2024"
     },
     {
       "source": "agint-agentic-graph-2025",
       "target": "masai-modular-architecture-2024"
     },
     {
       "source": "agint-agentic-graph-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "agint-agentic-graph-2025",
       "target": "challenges-paths-ai-2025"
     },
     {
       "source": "agint-agentic-graph-2025",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "agint-agentic-graph-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "agint-agentic-graph-2025",
       "target": "chatdev-communicative-agents-2023"
     },
     {
       "source": "agint-agentic-graph-2025",
       "target": "llm-agents-se-survey-2024"
     },
     {
       "source": "agint-agentic-graph-2025",
       "target": "tree-thoughts-deliberate-2023"
     },
     {
       "source": "agint-agentic-graph-2025",
       "target": "diversity-empowers-intelligence-2024"
     },
     {
       "source": "ai-alignment-contemporary-2025",
       "target": "constitutional-ai-2022"
     },
     {
       "source": "ai-alignment-strategies-2025",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "ai-alignment-strategies-2025",
       "target": "alignment-faking-2024"
     },
     {
       "source": "ai-alignment-strategies-2025",
       "target": "multiagent-risks-from-2025"
     },
     {
       "source": "ai-as-cognitive-2025",
       "target": "metr-rct-2025"
     },
     {
       "source": "ai-as-cognitive-2025",
       "target": "does-prompt-formatting-2024"
     },
     {
       "source": "ai-assistance-legal-2023",
       "target": "experimental-evidence-productivity-2023"
     },
     {
       "source": "ai-assistance-legal-2023",
       "target": "generative-ai-at-2023"
     },
     {
       "source": "ai-assistance-legal-2023",
       "target": "copilot-productivity-controlled-2023"
     },
     {
       "source": "ai-assistance-legal-2023",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "ai-code-maintainability-registered-report-2024",
       "target": "copilot-productivity-controlled-2023"
     },
     {
       "source": "ai-code-not-reproducible-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "ai-code-not-reproducible-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "ai-code-not-reproducible-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "ai-code-not-reproducible-2025",
       "target": "neurips-reproducibility-2021"
     },
     {
       "source": "ai-code-review-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "ai-code-survival-open-source-2026",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "ai-code-survival-open-source-2026",
       "target": "swe-bench-2023"
     },
     {
       "source": "ai-code-survival-open-source-2026",
       "target": "where-do-ai-2026"
     },
     {
       "source": "ai-code-survival-open-source-2026",
       "target": "rise-ai-teammates-2025"
     },
     {
       "source": "ai-code-survival-open-source-2026",
       "target": "copilot-code-quality-empirical-2023"
     },
     {
       "source": "ai-code-survival-open-source-2026",
       "target": "beyond-synthetic-benchmarks-2025"
     },
     {
       "source": "ai-code-wild-2025",
       "target": "copilot-productivity-controlled-2023"
     },
     {
       "source": "ai-code-wild-2025",
       "target": "copilot-security-weaknesses-2023"
     },
     {
       "source": "ai-code-wild-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "ai-code-wild-2025",
       "target": "codexity-secure-aiassisted-2024"
     },
     {
       "source": "ai-code-wild-2025",
       "target": "security-degradation-iterative-2025"
     },
     {
       "source": "ai-ides-vs-agents-impact-2026",
       "target": "metr-rct-2025"
     },
     {
       "source": "ai-ides-vs-agents-impact-2026",
       "target": "cursor-speed-quality-tradeoff-2025"
     },
     {
       "source": "ai-ides-vs-agents-impact-2026",
       "target": "code-me-me-2025"
     },
     {
       "source": "ai-ides-vs-agents-impact-2026",
       "target": "rise-ai-teammates-2025"
     },
     {
       "source": "ai-ides-vs-agents-impact-2026",
       "target": "aiassisted-programming-decreases-2025"
     },
     {
       "source": "ai-ides-vs-agents-impact-2026",
       "target": "how-much-does-2024"
     },
     {
       "source": "ai-ides-vs-agents-impact-2026",
       "target": "intuition-to-evidence-productivity-2025"
     },
     {
       "source": "ai-ides-vs-agents-impact-2026",
       "target": "agentic-ai-software-2025"
     },
     {
       "source": "ai-inference-falling-costs-2025",
       "target": "intelligence-per-watt-2025"
     },
     {
       "source": "ai-productivity-index-2025",
       "target": "paperbench-evaluating-ais-2025"
     },
     {
       "source": "ai-prs-code-quality-reuse-2026",
       "target": "rise-ai-teammates-2025"
     },
     {
       "source": "ai-prs-code-quality-reuse-2026",
       "target": "metr-rct-2025"
     },
     {
       "source": "ai-prs-code-quality-reuse-2026",
       "target": "swe-bench-2023"
     },
     {
       "source": "ai-safety-subproblems-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "ai-safety-subproblems-2023",
       "target": "constitutional-ai-2022"
     },
     {
       "source": "ai-scientist-fully-2024",
       "target": "swe-bench-2023"
     },
     {
       "source": "ai-scientist-fully-2024",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "ai-scientist-fully-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "ai-scientist-fully-2024",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "ai-scientistv2-workshoplevel-2025",
       "target": "ai-scientist-fully-2024"
     },
     {
       "source": "ai-scientistv2-workshoplevel-2025",
       "target": "mlebench-evaluating-machine-2024"
     },
     {
       "source": "ai-scientistv2-workshoplevel-2025",
       "target": "rebench-evaluating-frontier-2024"
     },
     {
       "source": "ai-scientistv2-workshoplevel-2025",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "ai-software-engineering-2025",
       "target": "navigating-complexity-generative-2023"
     },
     {
       "source": "ai-testing-should-2025",
       "target": "alignment-faking-2024"
     },
     {
       "source": "ai-testing-should-2025",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "ai-testing-should-2025",
       "target": "frontier-models-in-context-scheming-2024"
     },
     {
       "source": "aiassisted-code-editors-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "aiassisted-code-editors-2025",
       "target": "codebert-pretrained-model-2020"
     },
     {
       "source": "aiassisted-fixes-code-2025",
       "target": "automated-code-review-practice-2024"
     },
     {
       "source": "aiassisted-fixes-code-2025",
       "target": "llama-3-herd-2024"
     },
     {
       "source": "aiassisted-fixes-code-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "aiassisted-fixes-code-2025",
       "target": "copilot-productivity-controlled-2023"
     },
     {
       "source": "aiassisted-fixes-code-2025",
       "target": "how-much-does-2024"
     },
     {
       "source": "aiassisted-fixes-code-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "aiassisted-fixes-code-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "aiassisted-programming-decreases-2025",
       "target": "copilot-productivity-controlled-2023"
     },
     {
       "source": "aiassisted-programming-decreases-2025",
       "target": "impact-large-language-2024"
     },
     {
       "source": "aiassisted-programming-decreases-2025",
       "target": "cursor-speed-quality-tradeoff-2025"
     },
     {
       "source": "aiassisted-programming-decreases-2025",
       "target": "generative-ai-at-2023"
     },
     {
       "source": "aiassisted-programming-decreases-2025",
       "target": "vibe-coding-practice-2025"
     },
     {
       "source": "aidriven-scholarly-peer-2025",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "aidriven-scholarly-peer-2025",
       "target": "deepreview-improving-llmbased-2025"
     },
     {
       "source": "aidriven-software-engineering-2024",
       "target": "copilot-productivity-controlled-2023"
     },
     {
       "source": "aidriven-software-engineering-2024",
       "target": "alphacode-competition-level-2022"
     },
     {
       "source": "aidriven-software-engineering-2024",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "aime-ai-system-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "aime-ai-system-2024",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "aime-ai-system-2024",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "aime-ai-system-2024",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "ainative-software-engineering-2024",
       "target": "cursor-speed-quality-tradeoff-2025"
     },
     {
       "source": "ainative-software-engineering-2024",
       "target": "copilot-productivity-controlled-2023"
     },
     {
       "source": "ainative-software-engineering-2024",
       "target": "llms-se-systematic-review-2023"
     },
     {
       "source": "ainative-software-engineering-2024",
       "target": "openhands-ai-sw-agent-2024"
     },
     {
       "source": "ainative-software-engineering-2024",
       "target": "compilernext-searchbased-compiler-2025"
     },
     {
       "source": "ainstein-assessing-feasibility-2025",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "ainstein-assessing-feasibility-2025",
       "target": "emergent-abilities-mirage-2023"
     },
     {
       "source": "aipowered-code-review-2023",
       "target": "codebert-pretrained-model-2020"
     },
     {
       "source": "aipowered-code-review-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "ais-environmental-cost-2025",
       "target": "emergent-abilities-mirage-2023"
     },
     {
       "source": "aixamine-simplified-llm-2025",
       "target": "secodeplt-unified-platform-2024"
     },
     {
       "source": "aixamine-simplified-llm-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "aligned-query-expansion-2025",
       "target": "llama-3-herd-2024"
     },
     {
       "source": "aligned-query-expansion-2025",
       "target": "survey-hallucination-large-2023-2"
     },
     {
       "source": "aligned-query-expansion-2025",
       "target": "bayesian-reward-models-2024"
     },
     {
       "source": "aligning-objective-llmbased-2024",
       "target": "less-training-more-2022"
     },
     {
       "source": "aligning-objective-llmbased-2024",
       "target": "automated-program-repair-2023"
     },
     {
       "source": "aligning-objective-llmbased-2024",
       "target": "rapgen-retrievalaugmented-patch-2023"
     },
     {
       "source": "aligning-objective-llmbased-2024",
       "target": "copiloting-copilots-fusing-2023"
     },
     {
       "source": "aligning-objective-llmbased-2024",
       "target": "impact-code-language-2023"
     },
     {
       "source": "aligning-objective-llmbased-2024",
       "target": "survey-learningbased-automated-2023"
     },
     {
       "source": "alignment-faking-2024",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "alignment-faking-2024",
       "target": "frontier-models-in-context-scheming-2024"
     },
     {
       "source": "alignment-safety-llm-survey-2025",
       "target": "constitutional-ai-2022"
     },
     {
       "source": "alignment-safety-llm-survey-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "alignment-safety-llm-survey-2025",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "alignment-safety-llm-survey-2025",
       "target": "alignment-faking-2024"
     },
     {
       "source": "alleviating-fear-losing-2025",
       "target": "beavertails-improved-safety-2023"
     },
     {
       "source": "alphacode-competition-level-2022",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "alphacode-competition-level-2022",
       "target": "codebert-pretrained-model-2020"
     },
     {
       "source": "ambigswe-interactive-agents-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "ambigswe-interactive-agents-2025",
       "target": "openhands-ai-sw-agent-2024"
     },
     {
       "source": "ambigswe-interactive-agents-2025",
       "target": "copilot-productivity-controlled-2023"
     },
     {
       "source": "ambigswe-interactive-agents-2025",
       "target": "generative-ai-at-2023"
     },
     {
       "source": "ambigswe-interactive-agents-2025",
       "target": "clarifygpt-empowering-llmbased-2023"
     },
     {
       "source": "ambigswe-interactive-agents-2025",
       "target": "test-driven-interactive-code-gen-2024"
     },
     {
       "source": "ambigswe-interactive-agents-2025",
       "target": "ai-scientist-fully-2024"
     },
     {
       "source": "among-us-measuring-2026",
       "target": "improving-factuality-reasoning-2023"
     },
     {
       "source": "among-us-measuring-2026",
       "target": "adaptive-attacks-break-2025"
     },
     {
       "source": "among-us-measuring-2026",
       "target": "moco-onestop-shop-2026"
     },
     {
       "source": "among-us-sandbox-2025",
       "target": "alignment-faking-2024"
     },
     {
       "source": "among-us-sandbox-2025",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "among-us-sandbox-2025",
       "target": "chatbot-arena-open-2024"
     },
     {
       "source": "analysis-evaluation-synthetic-2025",
       "target": "scaling-laws-2020"
     },
     {
       "source": "analysis-research-status-2025",
       "target": "utboost-rigorous-evaluation-2025"
     },
     {
       "source": "analysis-studentllm-interaction-2025",
       "target": "empirical-study-usage-2024"
     },
     {
       "source": "analysis-studentllm-interaction-2025",
       "target": "llm-agents-se-survey-2024"
     },
     {
       "source": "anatomy-capability-emergence-2026",
       "target": "emergent-abilities-large-2022"
     },
     {
       "source": "anatomy-capability-emergence-2026",
       "target": "emergent-abilities-mirage-2023"
     },
     {
       "source": "ancoder-anchored-code-2026",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "ancoder-anchored-code-2026",
       "target": "qwen25coder-technical-report-2024"
     },
     {
       "source": "ancoder-anchored-code-2026",
       "target": "constrained-decoding-diffusion-2025"
     },
     {
       "source": "animagents-coordinating-multistage-2025",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "animagents-coordinating-multistage-2025",
       "target": "swe-agent-2024"
     },
     {
       "source": "animagents-coordinating-multistage-2025",
       "target": "mapcoder-multiagent-code-2024"
     },
     {
       "source": "animagents-coordinating-multistage-2025",
       "target": "survey-autonomous-llm-agents-2023"
     },
     {
       "source": "animagents-coordinating-multistage-2025",
       "target": "rise-potential-large-2023"
     },
     {
       "source": "animagents-coordinating-multistage-2025",
       "target": "multi-agent-collaboration-survey-2025"
     },
     {
       "source": "animagents-coordinating-multistage-2025",
       "target": "generative-ai-at-2023"
     },
     {
       "source": "annotation-alignment-comparing-2024",
       "target": "constitutional-ai-2022"
     },
     {
       "source": "annotation-alignment-comparing-2024",
       "target": "chatbot-arena-open-2024"
     },
     {
       "source": "antiregulatory-ai-how-2025",
       "target": "constitutional-ai-2022"
     },
     {
       "source": "antiregulatory-ai-how-2025",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "appatch-automated-adaptive-2024",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "appatch-automated-adaptive-2024",
       "target": "how-effective-neural-2023"
     },
     {
       "source": "applying-rlaif-code-2024",
       "target": "gorilla-large-language-2023"
     },
     {
       "source": "applying-rlaif-code-2024",
       "target": "constitutional-ai-2022"
     },
     {
       "source": "applying-rlaif-code-2024",
       "target": "toolformer-language-models-2023"
     },
     {
       "source": "applying-rlaif-code-2024",
       "target": "toolllm-facilitating-large-2023"
     },
     {
       "source": "appworld-controllable-world-2024",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "appworld-controllable-world-2024",
       "target": "swe-bench-2023"
     },
     {
       "source": "appworld-controllable-world-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "appworld-controllable-world-2024",
       "target": "toolllm-facilitating-large-2023"
     },
     {
       "source": "appworld-controllable-world-2024",
       "target": "executable-code-actions-2024"
     },
     {
       "source": "appworld-controllable-world-2024",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "appworld-controllable-world-2024",
       "target": "webarena-autonomous-agents-2023"
     },
     {
       "source": "appworld-controllable-world-2024",
       "target": "gorilla-large-language-2023"
     },
     {
       "source": "appworld-controllable-world-2024",
       "target": "osworld-benchmarking-multimodal-2024"
     },
     {
       "source": "apr-llm-survey-2025",
       "target": "agentless-2024"
     },
     {
       "source": "apr-llm-survey-2025",
       "target": "swe-agent-2024"
     },
     {
       "source": "apr-llm-survey-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "apr-llm-survey-2025",
       "target": "repairagent-llm-bug-repair-2024"
     },
     {
       "source": "apr-llm-survey-2025",
       "target": "openhands-ai-sw-agent-2024"
     },
     {
       "source": "apr-llm-survey-2025",
       "target": "repairllama-efficient-representations-2023"
     },
     {
       "source": "apr-llm-survey-2025",
       "target": "systematic-literature-review-2024"
     },
     {
       "source": "april-api-synthesis-2025",
       "target": "fuzz4all-universal-fuzzing-2023"
     },
     {
       "source": "aptserve-adaptive-request-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "aquallm-evaluating-accuracy-2025",
       "target": "not-what-youve-2023"
     },
     {
       "source": "aquallm-evaluating-accuracy-2025",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "arcmemo-abstract-reasoning-2025",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "arcmemo-abstract-reasoning-2025",
       "target": "voyager-open-ended-2023"
     },
     {
       "source": "arcmemo-abstract-reasoning-2025",
       "target": "memgpt-llms-as-2023"
     },
     {
       "source": "arcmemo-abstract-reasoning-2025",
       "target": "generative-agents-interactive-2023"
     },
     {
       "source": "arcs-agentic-retrievalaugmented-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "arcs-agentic-retrievalaugmented-2025",
       "target": "alphacode-competition-level-2022"
     },
     {
       "source": "arcs-agentic-retrievalaugmented-2025",
       "target": "empirical-study-retrievalaugmented-2025"
     },
     {
       "source": "arcs-agentic-retrievalaugmented-2025",
       "target": "enhancing-code-translation-2024"
     },
     {
       "source": "arcs-agentic-retrievalaugmented-2025",
       "target": "deepseek-coder-v2-2024"
     },
     {
       "source": "arena-hard-auto-2024",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "arena-hard-auto-2024",
       "target": "chatbot-arena-open-2024"
     },
     {
       "source": "arena-hard-auto-2024",
       "target": "swe-bench-2023"
     },
     {
       "source": "arena-hard-auto-2024",
       "target": "bigcodebench-2024"
     },
     {
       "source": "arena-hard-auto-2024",
       "target": "livecodebench-2024"
     },
     {
       "source": "arena-hard-auto-2024",
       "target": "agentbench-evaluating-llms-2023"
     },
     {
       "source": "arena-hard-auto-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "arena-hard-auto-2024",
       "target": "nlp-evaluation-trouble-2023"
     },
     {
       "source": "ares-automated-evaluation-2023",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "ares-automated-evaluation-2023",
       "target": "augmented-language-models-2023"
     },
     {
       "source": "argus-defending-against-2025",
       "target": "secalign-defending-against-2024"
     },
     {
       "source": "argus-defending-against-2025",
       "target": "agenttypo-adaptive-typographic-2025"
     },
     {
       "source": "argus-defending-against-2025",
       "target": "defense-against-prompt-2024"
     },
     {
       "source": "argus-defending-against-2025",
       "target": "can-indirect-prompt-2025"
     },
     {
       "source": "argus-defending-against-2025",
       "target": "defending-against-indirect-2024"
     },
     {
       "source": "argus-defending-against-2025",
       "target": "formalizing-benchmarking-prompt-2023"
     },
     {
       "source": "argus-defending-against-2025",
       "target": "manipulating-multimodal-agents-2025"
     },
     {
       "source": "arks-active-retrieval-2024",
       "target": "swe-bench-2023"
     },
     {
       "source": "arks-active-retrieval-2024",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "arks-active-retrieval-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "arks-active-retrieval-2024",
       "target": "starcoder-2023"
     },
     {
       "source": "arks-active-retrieval-2024",
       "target": "your-code-generated-2023"
     },
     {
       "source": "art-adaptive-response-2025",
       "target": "selfconsistency-improves-chain-2022"
     },
     {
       "source": "art-adaptive-response-2025",
       "target": "improving-factuality-reasoning-2023"
     },
     {
       "source": "art-adaptive-response-2025",
       "target": "tree-thoughts-deliberate-2023"
     },
     {
       "source": "art-adaptive-response-2025",
       "target": "constitutional-ai-2022"
     },
     {
       "source": "art-adaptive-response-2025",
       "target": "scaffolded-model-capability-2023"
     },
     {
       "source": "art-adaptive-response-2025",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "art-adaptive-response-2025",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "art-repair-optimizing-2025",
       "target": "automated-program-repair-2022"
     },
     {
       "source": "art-repair-optimizing-2025",
       "target": "repairagent-llm-bug-repair-2024"
     },
     {
       "source": "art-repair-optimizing-2025",
       "target": "repairllama-efficient-representations-2023"
     },
     {
       "source": "art-repair-optimizing-2025",
       "target": "automated-program-repair-2023"
     },
     {
       "source": "art-repair-optimizing-2025",
       "target": "cigar-costefficient-program-2024"
     },
     {
       "source": "art-scaling-test-time-compute-2025",
       "target": "compute-optimal-inference-2024"
     },
     {
       "source": "art-scaling-test-time-compute-2025",
       "target": "selfconsistency-improves-chain-2022"
     },
     {
       "source": "art-scaling-test-time-compute-2025",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "art-scaling-test-time-compute-2025",
       "target": "dont-overthink-it-2025"
     },
     {
       "source": "art-scaling-test-time-compute-2025",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "art-scaling-test-time-compute-2025",
       "target": "tree-thoughts-deliberate-2023"
     },
     {
       "source": "art-scaling-test-time-compute-2025",
       "target": "gpqa-graduatelevel-googleproof-2023"
     },
     {
       "source": "art-scaling-test-time-compute-2025",
       "target": "dapo-opensource-llm-2025"
     },
     {
       "source": "artifactsbench-bridging-visualinteractive-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "artifactsbench-bridging-visualinteractive-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "artifactsbench-bridging-visualinteractive-2025",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "artifactsbench-bridging-visualinteractive-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "artifactsbench-bridging-visualinteractive-2025",
       "target": "webbench-llm-code-2025"
     },
     {
       "source": "artifactsbench-bridging-visualinteractive-2025",
       "target": "webarena-autonomous-agents-2023"
     },
     {
       "source": "artifactsbench-bridging-visualinteractive-2025",
       "target": "codecriticbench-holistic-code-2025"
     },
     {
       "source": "artificial-brain-neuroscience-2026",
       "target": "uc-berkeley-mast-2025"
     },
     {
       "source": "artificial-brain-neuroscience-2026",
       "target": "scaffolded-model-capability-2023"
     },
     {
       "source": "artificial-human-intelligence-2025",
       "target": "generative-ai-at-2023"
     },
     {
       "source": "artificial-human-intelligence-2025",
       "target": "canaries-coal-mine-2025"
     },
     {
       "source": "artificial-human-intelligence-2025",
       "target": "experimental-evidence-productivity-2023"
     },
     {
       "source": "artificial-human-intelligence-2025",
       "target": "emergent-abilities-large-2022"
     },
     {
       "source": "artificial-human-intelligence-2025",
       "target": "emergent-abilities-mirage-2023"
     },
     {
       "source": "artificial-intelligence-assistance-2026",
       "target": "attention-is-all-you-need-2017"
     },
     {
       "source": "artificial-just-artful-2025",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "artificial-just-artful-2025",
       "target": "bigcodebench-2024"
     },
     {
       "source": "artificial-just-artful-2025",
       "target": "rethinking-verification-llm-2025"
     },
     {
       "source": "artificial-just-artful-2025",
       "target": "hallucination-by-code-2025"
     },
     {
       "source": "artificial-just-artful-2025",
       "target": "survey-llm-code-generation-2025"
     },
     {
       "source": "artificial-organisations-2026",
       "target": "constitutional-ai-2022"
     },
     {
       "source": "artificial-organisations-2026",
       "target": "improving-factuality-reasoning-2023"
     },
     {
       "source": "artificial-organisations-2026",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "artificial-organisations-2026",
       "target": "autogen-multi-agent-2023"
     },
     {
       "source": "artificial-organisations-2026",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "artificial-organisations-2026",
       "target": "camel-communicative-agents-2023"
     },
     {
       "source": "ask-me-anything-2022",
       "target": "selfconsistency-improves-chain-2022"
     },
     {
       "source": "ask-me-anything-2022",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "ask-me-anything-2022",
       "target": "emergent-abilities-large-2022"
     },
     {
       "source": "ask-me-anything-2022",
       "target": "scaling-laws-2020"
     },
     {
       "source": "askeda-design-assistant-2024",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "askeda-design-assistant-2024",
       "target": "granite-code-models-2024"
     },
     {
       "source": "assessing-answerability-queries-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "assessing-answerability-queries-2024",
       "target": "selfcheckgpt-zeroresource-blackbox-2023"
     },
     {
       "source": "assessing-correctness-llmbased-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "assessing-correctness-llmbased-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "assessing-correctness-llmbased-2025",
       "target": "your-code-generated-2023"
     },
     {
       "source": "assessing-domainlevel-susceptibility-2026",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "assessing-domainlevel-susceptibility-2026",
       "target": "poisoning-attacks-llms-2025"
     },
     {
       "source": "assessing-domainlevel-susceptibility-2026",
       "target": "thinking-llms-lie-2025"
     },
     {
       "source": "assessing-domainlevel-susceptibility-2026",
       "target": "exposing-privacy-gaps-2024"
     },
     {
       "source": "assessing-impact-code-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "assessing-impact-code-2025",
       "target": "data-contamination-benchmarks-2023"
     },
     {
       "source": "assessing-impact-code-2025",
       "target": "your-code-generated-2023"
     },
     {
       "source": "assessing-impact-code-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "assessing-latent-automated-2024",
       "target": "impact-code-language-2023"
     },
     {
       "source": "assessing-latent-automated-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "assessing-latent-automated-2024",
       "target": "automated-program-repair-2022"
     },
     {
       "source": "assessing-latent-automated-2024",
       "target": "automated-program-repair-2023"
     },
     {
       "source": "assessing-latent-automated-2024",
       "target": "less-training-more-2022"
     },
     {
       "source": "assessing-latent-automated-2024",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "assessing-latent-automated-2024",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "assessing-latent-automated-2024",
       "target": "starcoder-2023"
     },
     {
       "source": "assessing-latent-automated-2024",
       "target": "survey-learningbased-automated-2023"
     },
     {
       "source": "assessing-verifying-task-2024",
       "target": "autogen-multi-agent-2023"
     },
     {
       "source": "assessing-verifying-task-2024",
       "target": "agentbench-evaluating-llms-2023"
     },
     {
       "source": "assessing-verifying-task-2024",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "assessing-verifying-task-2024",
       "target": "chateval-better-llmbased-2023"
     },
     {
       "source": "assessing-verifying-task-2024",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "assessing-verifying-task-2024",
       "target": "camel-communicative-agents-2023"
     },
     {
       "source": "astrovisbench-code-benchmark-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "astrovisbench-code-benchmark-2025",
       "target": "bigcodebench-2024"
     },
     {
       "source": "astrovisbench-code-benchmark-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "astrovisbench-code-benchmark-2025",
       "target": "ai-scientist-fully-2024"
     },
     {
       "source": "astrovisbench-code-benchmark-2025",
       "target": "paperbench-evaluating-ais-2025"
     },
     {
       "source": "astrovisbench-code-benchmark-2025",
       "target": "mlebench-evaluating-machine-2024"
     },
     {
       "source": "astrovisbench-code-benchmark-2025",
       "target": "matplotagent-method-evaluation-2024"
     },
     {
       "source": "astrovisbench-code-benchmark-2025",
       "target": "your-code-generated-2023"
     },
     {
       "source": "asymptotic-study-incontext-2025",
       "target": "attention-is-all-you-need-2017"
     },
     {
       "source": "asymptotic-study-incontext-2025",
       "target": "emergent-abilities-large-2022"
     },
     {
       "source": "asymptotic-study-incontext-2025",
       "target": "emergent-abilities-mirage-2023"
     },
     {
       "source": "atlas-artifact-generation-2025",
       "target": "guiding-llms-right-2024"
     },
     {
       "source": "atlas-artifact-generation-2025",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "atlas-artifact-generation-2025",
       "target": "llms-se-systematic-review-2023"
     },
     {
       "source": "atlas-artifact-generation-2025",
       "target": "no-need-lift-2023"
     },
     {
       "source": "atom-thoughts-markov-2025",
       "target": "tree-thoughts-deliberate-2023"
     },
     {
       "source": "atom-thoughts-markov-2025",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "atom-thoughts-markov-2025",
       "target": "compute-optimal-inference-2024"
     },
     {
       "source": "atom-thoughts-markov-2025",
       "target": "selfconsistency-improves-chain-2022"
     },
     {
       "source": "atom-thoughts-markov-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "atom-thoughts-markov-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "atom-thoughts-markov-2025",
       "target": "more-llm-calls-2024"
     },
     {
       "source": "attacking-llms-ai-2025",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "attacking-llms-ai-2025",
       "target": "not-what-youve-2023"
     },
     {
       "source": "attacks-by-content-2025",
       "target": "not-what-youve-2023"
     },
     {
       "source": "attacks-by-content-2025",
       "target": "secalign-defending-against-2024"
     },
     {
       "source": "attacks-by-content-2025",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "attention-all-you-2025",
       "target": "formalizing-benchmarking-prompt-2023"
     },
     {
       "source": "attention-all-you-2025",
       "target": "secalign-defending-against-2024"
     },
     {
       "source": "attention-all-you-2025",
       "target": "attention-tracker-detecting-2024"
     },
     {
       "source": "attention-all-you-2025",
       "target": "neural-exec-learning-2024"
     },
     {
       "source": "attention-all-you-2025",
       "target": "not-what-youve-2023"
     },
     {
       "source": "attention-all-you-2025",
       "target": "injecguard-benchmarking-mitigating-2024"
     },
     {
       "source": "attention-pruning-automated-2025",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "attention-tracker-detecting-2024",
       "target": "formalizing-benchmarking-prompt-2023"
     },
     {
       "source": "attention-tracker-detecting-2024",
       "target": "not-what-youve-2023"
     },
     {
       "source": "attention-tracker-detecting-2024",
       "target": "prompt-injection-attacks-2024"
     },
     {
       "source": "attention-tracker-detecting-2024",
       "target": "jatmo-prompt-injection-2023"
     },
     {
       "source": "attention-tracker-detecting-2024",
       "target": "automatic-universal-prompt-2024"
     },
     {
       "source": "attention-tracker-detecting-2024",
       "target": "neural-exec-learning-2024"
     },
     {
       "source": "audit-trails-accountability-2026",
       "target": "emergent-abilities-mirage-2023"
     },
     {
       "source": "auditing-fairness-under-2026",
       "target": "emergent-abilities-mirage-2023"
     },
     {
       "source": "augmented-language-models-2023",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "augmented-language-models-2023",
       "target": "toolformer-language-models-2023"
     },
     {
       "source": "augmented-language-models-2023",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "augmented-language-models-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "autocodebench-large-language-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "autocodebench-large-language-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "autocodebench-large-language-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "autocodebench-large-language-2025",
       "target": "bigcodebench-2024"
     },
     {
       "source": "autocodebench-large-language-2025",
       "target": "deepseek-coder-v2-2024"
     },
     {
       "source": "autocodebench-large-language-2025",
       "target": "qwen25coder-technical-report-2024"
     },
     {
       "source": "autocypher-improving-llms-2024",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "autocypher-improving-llms-2024",
       "target": "wizardcoder-empowering-code-2023"
     },
     {
       "source": "autocypher-improving-llms-2024",
       "target": "llama-3-herd-2024"
     },
     {
       "source": "autocypher-improving-llms-2024",
       "target": "qwen25coder-technical-report-2024"
     },
     {
       "source": "autoflow-automated-workflow-2024",
       "target": "autogen-multi-agent-2023"
     },
     {
       "source": "autoflow-automated-workflow-2024",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "autoflow-automated-workflow-2024",
       "target": "dspy-compiling-declarative-2023"
     },
     {
       "source": "autoflow-automated-workflow-2024",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "autoflow-automated-workflow-2024",
       "target": "camel-communicative-agents-2023"
     },
     {
       "source": "autoflow-automated-workflow-2024",
       "target": "chatdev-communicative-agents-2023"
     },
     {
       "source": "autoflow-automated-workflow-2024",
       "target": "survey-autonomous-llm-agents-2023"
     },
     {
       "source": "autoflow-automated-workflow-2024",
       "target": "tree-thoughts-deliberate-2023"
     },
     {
       "source": "autogen-enabling-nextgen-2023",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "autogen-enabling-nextgen-2023",
       "target": "improving-factuality-reasoning-2023"
     },
     {
       "source": "autogen-enabling-nextgen-2023",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "autogen-enabling-nextgen-2023",
       "target": "voyager-open-ended-2023"
     },
     {
       "source": "autogen-enabling-nextgen-2023",
       "target": "generative-agents-interactive-2023"
     },
     {
       "source": "autogen-enabling-nextgen-2023",
       "target": "rise-potential-large-2023"
     },
     {
       "source": "autogen-enabling-nextgen-2023",
       "target": "survey-autonomous-llm-agents-2023"
     },
     {
       "source": "autogen-multi-agent-2023",
       "target": "improving-factuality-reasoning-2023"
     },
     {
       "source": "autogen-multi-agent-2023",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "autogen-multi-agent-2023",
       "target": "voyager-open-ended-2023"
     },
     {
       "source": "autogen-multi-agent-2023",
       "target": "generative-agents-interactive-2023"
     },
     {
       "source": "autogen-multi-agent-2023",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "autogen-multi-agent-2023",
       "target": "rise-potential-large-2023"
     },
     {
       "source": "autogen-multi-agent-2023",
       "target": "survey-autonomous-llm-agents-2023"
     },
     {
       "source": "autokaggle-multiagent-framework-2024",
       "target": "mlebench-evaluating-machine-2024"
     },
     {
       "source": "autokaggle-multiagent-framework-2024",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "autokaggle-multiagent-framework-2024",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "autokaggle-multiagent-framework-2024",
       "target": "camel-communicative-agents-2023"
     },
     {
       "source": "autokaggle-multiagent-framework-2024",
       "target": "rise-potential-large-2023"
     },
     {
       "source": "automated-bug-detection-2025",
       "target": "survey-learningbased-automated-2023"
     },
     {
       "source": "automated-bug-detection-2025",
       "target": "codebert-pretrained-model-2020"
     },
     {
       "source": "automated-cc-program-2024",
       "target": "automated-program-repair-2022"
     },
     {
       "source": "automated-code-generation-2025",
       "target": "llmbased-retrievalaugmented-control-2024"
     },
     {
       "source": "automated-code-generation-2025",
       "target": "reacc-retrievalaugmented-code-2022"
     },
     {
       "source": "automated-code-review-practice-2024",
       "target": "aiassisted-assessment-coding-2024"
     },
     {
       "source": "automated-code-review-practice-2024",
       "target": "aipowered-code-review-2024"
     },
     {
       "source": "automated-code-review-practice-2024",
       "target": "tales-from-trenches-2024"
     },
     {
       "source": "automated-code-review-practice-2024",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "automated-discovery-test-2025",
       "target": "fuzz4all-universal-fuzzing-2023"
     },
     {
       "source": "automated-discovery-test-2025",
       "target": "automated-program-repair-2023"
     },
     {
       "source": "automated-extraction-mechanical-2026",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "automated-extraction-mechanical-2026",
       "target": "rise-potential-large-2023"
     },
     {
       "source": "automated-extraction-mechanical-2026",
       "target": "efficient-guided-generation-2023"
     },
     {
       "source": "automated-formalization-conceptual-2025",
       "target": "deepseek-v3-2024"
     },
     {
       "source": "automated-knowledge-component-2025",
       "target": "codebert-pretrained-model-2020"
     },
     {
       "source": "automated-knowledge-component-2025",
       "target": "llama-3-herd-2024"
     },
     {
       "source": "automated-program-repair-2022",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "automated-program-repair-2022",
       "target": "less-training-more-2022"
     },
     {
       "source": "automated-program-repair-2022",
       "target": "alphacode-competition-level-2022"
     },
     {
       "source": "automated-program-repair-2022",
       "target": "scaling-laws-2020"
     },
     {
       "source": "automated-program-repair-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "automated-program-repair-2023",
       "target": "automated-program-repair-2022"
     },
     {
       "source": "automated-program-repair-2023",
       "target": "less-training-more-2022"
     },
     {
       "source": "automated-program-repair-2023-2",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "automated-program-repair-2024",
       "target": "automated-program-repair-2022"
     },
     {
       "source": "automated-program-repair-2024",
       "target": "less-training-more-2022"
     },
     {
       "source": "automated-program-repair-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "automated-program-repair-2024",
       "target": "runbugrun-executable-dataset-2023"
     },
     {
       "source": "automated-program-repair-2024",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "automated-program-repair-2024",
       "target": "multiple-scalable-polyglot-2023"
     },
     {
       "source": "automated-program-repair-2024",
       "target": "impact-code-language-2023"
     },
     {
       "source": "automated-program-repair-2025",
       "target": "automated-program-repair-2022"
     },
     {
       "source": "automated-program-repair-2025-2",
       "target": "automated-program-repair-2023-3"
     },
     {
       "source": "automated-program-repair-2025-2",
       "target": "automated-program-repair-2024-3"
     },
     {
       "source": "automated-repair-c-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "automated-repair-c-2025",
       "target": "automated-program-repair-2023"
     },
     {
       "source": "automated-repair-c-2025",
       "target": "contrastrepair-enhancing-conversationbased-2024"
     },
     {
       "source": "automated-repair-c-2025",
       "target": "agentless-2024"
     },
     {
       "source": "automated-repair-c-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "automated-repair-c-2025",
       "target": "cigar-costefficient-program-2024"
     },
     {
       "source": "automated-repair-c-2025",
       "target": "aligning-objective-llmbased-2024"
     },
     {
       "source": "automated-repair-c-2025",
       "target": "copiloting-copilots-fusing-2023"
     },
     {
       "source": "automated-smart-contract-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "automated-smart-contract-2025",
       "target": "deepseek-coder-2024"
     },
     {
       "source": "automated-smart-contract-2025",
       "target": "code-llama-2023"
     },
     {
       "source": "automated-smart-contract-2025",
       "target": "repocoder-repositorylevel-code-2023"
     },
     {
       "source": "automated-smart-contract-2025",
       "target": "soleval-benchmarking-large-2025"
     },
     {
       "source": "automated-smart-contract-2025",
       "target": "starcoder-2023"
     },
     {
       "source": "automated-structural-testing-2026",
       "target": "uc-berkeley-mast-2025"
     },
     {
       "source": "automated-structural-testing-2026",
       "target": "testdriven-development-llmbased-2024"
     },
     {
       "source": "automated-structural-testing-2026",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "automated-test-case-2024",
       "target": "llms-se-systematic-review-2023"
     },
     {
       "source": "automated-test-case-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "automated-test-case-2024",
       "target": "impact-code-language-2023"
     },
     {
       "source": "automated-test-case-2024",
       "target": "survey-learningbased-automated-2023"
     },
     {
       "source": "automated-test-case-2024",
       "target": "less-training-more-2022"
     },
     {
       "source": "automated-test-generation-2024",
       "target": "autogen-multi-agent-2023"
     },
     {
       "source": "automated-test-generation-2024",
       "target": "agentbench-evaluating-llms-2023"
     },
     {
       "source": "automated-test-generation-2024",
       "target": "toolllm-facilitating-large-2023"
     },
     {
       "source": "automated-test-generation-2024",
       "target": "gorilla-large-language-2023"
     },
     {
       "source": "automated-test-generation-2024",
       "target": "your-code-generated-2023"
     },
     {
       "source": "automated-test-generation-2024",
       "target": "beyond-functional-correctness-2024"
     },
     {
       "source": "automated-test-generation-2024",
       "target": "gaia-benchmark-general-2023"
     },
     {
       "source": "automated-unit-test-2024",
       "target": "no-more-manual-2023"
     },
     {
       "source": "automated-unit-test-2024",
       "target": "adaptive-test-generation-2023"
     },
     {
       "source": "automated-unit-test-2024",
       "target": "codamosa-escaping-coverage-2023"
     },
     {
       "source": "automated-unit-test-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "automated-unit-test-2024",
       "target": "code-llama-2023"
     },
     {
       "source": "automatic-generation-benchmarks-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "automatic-generation-benchmarks-2024",
       "target": "crosscodeeval-diverse-multilingual-2023"
     },
     {
       "source": "automatic-generation-benchmarks-2024",
       "target": "swe-bench-2023"
     },
     {
       "source": "automatic-universal-prompt-2024",
       "target": "not-what-youve-2023"
     },
     {
       "source": "automatic-universal-prompt-2024",
       "target": "formalizing-benchmarking-prompt-2023"
     },
     {
       "source": "automatic-universal-prompt-2024",
       "target": "prompt-injection-llm-apps-2023"
     },
     {
       "source": "automatic-universal-prompt-2024",
       "target": "jatmo-prompt-injection-2023"
     },
     {
       "source": "automatically-benchmarking-code-agents-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "automatically-benchmarking-code-agents-2025",
       "target": "mlebench-evaluating-machine-2024"
     },
     {
       "source": "automatically-benchmarking-code-agents-2025",
       "target": "paperbench-evaluating-ais-2025"
     },
     {
       "source": "automatically-benchmarking-code-agents-2025",
       "target": "agentasajudge-evaluate-agents-2024"
     },
     {
       "source": "automatically-benchmarking-code-agents-2025",
       "target": "corecodebench-decoupling-code-2025"
     },
     {
       "source": "automatically-benchmarking-code-agents-2025",
       "target": "agentbased-evaluation-framework-2025"
     },
     {
       "source": "automatically-benchmarking-code-agents-2025",
       "target": "projecteval-benchmark-programming-2025"
     },
     {
       "source": "automatically-benchmarking-code-agents-2025",
       "target": "bigcodebench-2024"
     },
     {
       "source": "automatically-generating-web-2025",
       "target": "demystifying-llmbased-software-2025"
     },
     {
       "source": "automatically-generating-web-2025",
       "target": "testdriven-development-llmbased-2024"
     },
     {
       "source": "automatically-generating-web-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "automatically-generating-web-2025",
       "target": "survey-code-gen-llm-agents-2025"
     },
     {
       "source": "automatically-generating-web-2025",
       "target": "repairagent-llm-bug-repair-2024"
     },
     {
       "source": "automatically-generating-web-2025",
       "target": "metr-rct-2025"
     },
     {
       "source": "automatically-surfacing-opportunities-2025",
       "target": "uc-berkeley-mast-2025"
     },
     {
       "source": "automatically-surfacing-opportunities-2025",
       "target": "llama-3-herd-2024"
     },
     {
       "source": "automating-deception-scalable-2025",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "automating-rest-api-2024",
       "target": "automated-unit-test-2024"
     },
     {
       "source": "automating-structural-engineering-2025",
       "target": "autogen-multi-agent-2023"
     },
     {
       "source": "automating-structural-engineering-2025",
       "target": "uc-berkeley-mast-2025"
     },
     {
       "source": "automating-structural-engineering-2025",
       "target": "magenticone-generalist-multiagent-2024"
     },
     {
       "source": "automating-structural-engineering-2025",
       "target": "chatdev-communicative-agents-2023"
     },
     {
       "source": "automating-structural-engineering-2025",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "automating-structural-engineering-2025",
       "target": "hyperagent-generalist-software-2024"
     },
     {
       "source": "automating-structural-engineering-2025",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "automating-structural-engineering-2025",
       "target": "tree-thoughts-deliberate-2023"
     },
     {
       "source": "automating-structural-engineering-2025",
       "target": "compounding-reliability-2025"
     },
     {
       "source": "automation-ai-intergenerational-2025",
       "target": "generative-ai-at-2023"
     },
     {
       "source": "automation-ai-intergenerational-2025",
       "target": "experimental-evidence-productivity-2023"
     },
     {
       "source": "automation-ai-intergenerational-2025",
       "target": "copilot-productivity-controlled-2023"
     },
     {
       "source": "autonomous-normative-multiagent-2025",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "autonomous-normative-multiagent-2025",
       "target": "chatdev-communicative-agents-2023"
     },
     {
       "source": "autonomous-normative-multiagent-2025",
       "target": "large-language-model-2024"
     },
     {
       "source": "autonomous-normative-multiagent-2025",
       "target": "survey-llm-code-generation-2025"
     },
     {
       "source": "autonomous-normative-multiagent-2025",
       "target": "survey-hallucination-large-2023-2"
     },
     {
       "source": "autonomous-supplier-evaluation-2025",
       "target": "attention-is-all-you-need-2017"
     },
     {
       "source": "autop2c-llmbased-agent-2025",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "autop2c-llmbased-agent-2025",
       "target": "autogen-multi-agent-2023"
     },
     {
       "source": "autop2c-llmbased-agent-2025",
       "target": "swe-agent-2024"
     },
     {
       "source": "autop2c-llmbased-agent-2025",
       "target": "your-code-generated-2023"
     },
     {
       "source": "autop2c-llmbased-agent-2025",
       "target": "paperbench-evaluating-ais-2025"
     },
     {
       "source": "autop2c-llmbased-agent-2025",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "autop2c-llmbased-agent-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "autostreampipe-llm-assisted-2025",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "autostreampipe-llm-assisted-2025",
       "target": "tree-thoughts-deliberate-2023"
     },
     {
       "source": "autostreampipe-llm-assisted-2025",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "autostreampipe-llm-assisted-2025",
       "target": "code-llama-2023"
     },
     {
       "source": "autostreampipe-llm-assisted-2025",
       "target": "alphacode-competition-level-2022"
     },
     {
       "source": "autostreampipe-llm-assisted-2025",
       "target": "survey-code-gen-llm-agents-2025"
     },
     {
       "source": "autostreampipe-llm-assisted-2025",
       "target": "starcoder-2023"
     },
     {
       "source": "autostreampipe-llm-assisted-2025",
       "target": "autoflow-automated-workflow-2024"
     },
     {
       "source": "autotom-scaling-modelbased-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "autotom-scaling-modelbased-2025",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "autotom-scaling-modelbased-2025",
       "target": "llama-3-herd-2024"
     },
     {
       "source": "autovcoder-systematic-framework-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "autovcoder-systematic-framework-2024",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "autovcoder-systematic-framework-2024",
       "target": "verilogeval-evaluating-large-2023"
     },
     {
       "source": "autovcoder-systematic-framework-2024",
       "target": "benchmarking-large-language-2022"
     },
     {
       "source": "autovcoder-systematic-framework-2024",
       "target": "code-llama-2023"
     },
     {
       "source": "autovcoder-systematic-framework-2024",
       "target": "deepseek-coder-2024"
     },
     {
       "source": "autoverus-automated-proof-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "autoverus-automated-proof-2024",
       "target": "your-code-generated-2023"
     },
     {
       "source": "autoverus-automated-proof-2024",
       "target": "automated-program-repair-2023"
     },
     {
       "source": "awcp-workspace-delegation-2026",
       "target": "survey-autonomous-llm-agents-2023"
     },
     {
       "source": "awcp-workspace-delegation-2026",
       "target": "uc-berkeley-mast-2025"
     },
     {
       "source": "awcp-workspace-delegation-2026",
       "target": "autogen-multi-agent-2023"
     },
     {
       "source": "awcp-workspace-delegation-2026",
       "target": "swe-bench-2023"
     },
     {
       "source": "awcp-workspace-delegation-2026",
       "target": "swe-agent-2024"
     },
     {
       "source": "awcp-workspace-delegation-2026",
       "target": "openhands-ai-sw-agent-2024"
     },
     {
       "source": "awcp-workspace-delegation-2026",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "awcp-workspace-delegation-2026",
       "target": "engineering-multiagent-llms-2025"
     },
     {
       "source": "backdoor-attribution-elucidating-2025",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "backdoor-attribution-elucidating-2025",
       "target": "trustworthy-llm-agents-survey-2025"
     },
     {
       "source": "backdoor-samples-detection-2025",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "backdoored-retrievers-prompt-2024",
       "target": "not-what-youve-2023"
     },
     {
       "source": "backdoored-retrievers-prompt-2024",
       "target": "prompt-injection-llm-apps-2023"
     },
     {
       "source": "backdoored-retrievers-prompt-2024",
       "target": "survey-large-language-2023"
     },
     {
       "source": "backdooring-bias-large-2026",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "backdooring-bias-large-2026",
       "target": "poisoning-attacks-llms-2025"
     },
     {
       "source": "backdooring-bias-large-2026",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "backdoorpowered-prompt-injection-2025",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "backdoorpowered-prompt-injection-2025",
       "target": "secalign-defending-against-2024"
     },
     {
       "source": "backdoorpowered-prompt-injection-2025",
       "target": "formalizing-benchmarking-prompt-2023"
     },
     {
       "source": "backportbench-multilingual-benchmark-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "backportbench-multilingual-benchmark-2025",
       "target": "swe-agent-2024"
     },
     {
       "source": "backportbench-multilingual-benchmark-2025",
       "target": "agentless-2024"
     },
     {
       "source": "backportbench-multilingual-benchmark-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "backportbench-multilingual-benchmark-2025",
       "target": "openhands-ai-sw-agent-2024"
     },
     {
       "source": "backportbench-multilingual-benchmark-2025",
       "target": "llm-agents-se-survey-2024"
     },
     {
       "source": "backportbench-multilingual-benchmark-2025",
       "target": "survey-code-gen-llm-agents-2025"
     },
     {
       "source": "bamas-structuring-budgetaware-2025",
       "target": "autogen-multi-agent-2023"
     },
     {
       "source": "bamas-structuring-budgetaware-2025",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "bamas-structuring-budgetaware-2025",
       "target": "chatdev-communicative-agents-2023"
     },
     {
       "source": "bamas-structuring-budgetaware-2025",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "bamas-structuring-budgetaware-2025",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "bamas-structuring-budgetaware-2025",
       "target": "tree-thoughts-deliberate-2023"
     },
     {
       "source": "bamas-structuring-budgetaware-2025",
       "target": "llm-agents-se-survey-2024"
     },
     {
       "source": "bamboo-comprehensive-benchmark-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "bamboo-comprehensive-benchmark-2023",
       "target": "lost-middle-how-2023"
     },
     {
       "source": "bamboo-comprehensive-benchmark-2023",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "banglaforge-llm-collaboration-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "banglaforge-llm-collaboration-2025",
       "target": "tigercoder-novel-suite-2025"
     },
     {
       "source": "bashexplainer-retrievalaugmented-bash-2022",
       "target": "codebert-pretrained-model-2020"
     },
     {
       "source": "battleagentbench-benchmark-evaluating-2024",
       "target": "agentbench-evaluating-llms-2023"
     },
     {
       "source": "battleagentbench-benchmark-evaluating-2024",
       "target": "autogen-multi-agent-2023"
     },
     {
       "source": "battleagentbench-benchmark-evaluating-2024",
       "target": "large-language-model-2024"
     },
     {
       "source": "battleagentbench-benchmark-evaluating-2024",
       "target": "building-cooperative-embodied-2023"
     },
     {
       "source": "battleagentbench-benchmark-evaluating-2024",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "beavertails-improved-safety-2023",
       "target": "constitutional-ai-2022"
     },
     {
       "source": "behavior-alignment-new-2024",
       "target": "emergent-abilities-large-2022"
     },
     {
       "source": "bench-benchmark-toolagentuser-2024",
       "target": "swe-bench-2023"
     },
     {
       "source": "bench-benchmark-toolagentuser-2024",
       "target": "agentbench-evaluating-llms-2023"
     },
     {
       "source": "bench-benchmark-toolagentuser-2024",
       "target": "webarena-autonomous-agents-2023"
     },
     {
       "source": "bench-benchmark-toolagentuser-2024",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "bench-benchmark-toolagentuser-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "bench-benchmark-toolagentuser-2024",
       "target": "autogen-multi-agent-2023"
     },
     {
       "source": "bench-benchmark-toolagentuser-2024",
       "target": "generative-agents-interactive-2023"
     },
     {
       "source": "bench-benchmark-toolagentuser-2024",
       "target": "toolformer-language-models-2023"
     },
     {
       "source": "benchmark-contamination-survey-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "benchmark-contamination-survey-2024",
       "target": "quantifying-contamination-evaluating-2024"
     },
     {
       "source": "benchmark-contamination-survey-2024",
       "target": "livecodebench-2024"
     },
     {
       "source": "benchmark-contamination-survey-2024",
       "target": "top-leaderboard-ranking-2024"
     },
     {
       "source": "benchmark-contamination-survey-2024",
       "target": "chatbot-arena-open-2024"
     },
     {
       "source": "benchmark-contamination-survey-2024",
       "target": "rethinking-benchmark-contamination-2023"
     },
     {
       "source": "benchmark-contamination-survey-2024",
       "target": "concerned-data-contamination-2024"
     },
     {
       "source": "benchmark-contamination-survey-2024",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "benchmark-expertlevel-academic-2025",
       "target": "mmlu-measuring-massive-2020"
     },
     {
       "source": "benchmark-expertlevel-academic-2025",
       "target": "gpqa-graduatelevel-googleproof-2023"
     },
     {
       "source": "benchmark-expertlevel-academic-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "benchmark-expertlevel-academic-2025",
       "target": "frontiermath-benchmark-evaluating-2024"
     },
     {
       "source": "benchmark-expertlevel-academic-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "benchmark-expertlevel-academic-2025",
       "target": "mlebench-evaluating-machine-2024"
     },
     {
       "source": "benchmark-expertlevel-academic-2025",
       "target": "rebench-evaluating-frontier-2024"
     },
     {
       "source": "benchmark-test-time-scaling-agents-2026",
       "target": "swe-bench-2023"
     },
     {
       "source": "benchmark-test-time-scaling-agents-2026",
       "target": "swe-bench-plus-2024"
     },
     {
       "source": "benchmark-test-time-scaling-agents-2026",
       "target": "swe-agent-2024"
     },
     {
       "source": "benchmark-test-time-scaling-agents-2026",
       "target": "compute-optimal-inference-2024"
     },
     {
       "source": "benchmark-test-time-scaling-agents-2026",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "benchmark-test-time-scaling-agents-2026",
       "target": "gaia-benchmark-general-2023"
     },
     {
       "source": "benchmark-test-time-scaling-agents-2026",
       "target": "agentbench-evaluating-llms-2023"
     },
     {
       "source": "benchmarking-ai-models-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "benchmarking-ai-models-2025",
       "target": "your-code-generated-2023"
     },
     {
       "source": "benchmarking-ai-models-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "benchmarking-ai-models-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "benchmarking-ai-models-2025",
       "target": "agentbench-evaluating-llms-2023"
     },
     {
       "source": "benchmarking-ai-models-2025",
       "target": "top-leaderboard-ranking-2024"
     },
     {
       "source": "benchmarking-ai-models-2025",
       "target": "codeelo-benchmarking-competitionlevel-2025"
     },
     {
       "source": "benchmarking-ai-models-2025-2",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "benchmarking-ai-models-2025-2",
       "target": "your-code-generated-2023"
     },
     {
       "source": "benchmarking-ai-models-2025-2",
       "target": "livecodebench-2024"
     },
     {
       "source": "benchmarking-ai-models-2025-2",
       "target": "swe-bench-2023"
     },
     {
       "source": "benchmarking-ai-models-2025-2",
       "target": "agentbench-evaluating-llms-2023"
     },
     {
       "source": "benchmarking-ai-models-2025-2",
       "target": "bigcodebench-2024"
     },
     {
       "source": "benchmarking-ai-models-2025-2",
       "target": "top-leaderboard-ranking-2024"
     },
     {
       "source": "benchmarking-ai-models-2025-2",
       "target": "alphacode-competition-level-2022"
     },
     {
       "source": "benchmarking-epistemology-construct-2025",
       "target": "emergent-abilities-mirage-2023"
     },
     {
       "source": "benchmarking-hallucination-large-2024",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "benchmarking-hallucination-large-2024",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "benchmarking-large-language-2022",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "benchmarking-large-language-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "benchmarking-large-language-2024",
       "target": "frontiermath-benchmark-evaluating-2024"
     },
     {
       "source": "benchmarking-large-language-2024",
       "target": "arcs-agentic-retrievalaugmented-2025"
     },
     {
       "source": "benchmarking-large-language-2024",
       "target": "enhancing-code-translation-2024"
     },
     {
       "source": "benchmarking-llms-unit-2025",
       "target": "testgeneval-real-world-2024"
     },
     {
       "source": "benchmarking-llms-unit-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "benchmarking-llms-unit-2025",
       "target": "swtbench-testing-validating-2024"
     },
     {
       "source": "benchmarking-llms-unit-2025",
       "target": "lessleakbench-first-investigation-2025"
     },
     {
       "source": "benchmarking-llms-unit-2025",
       "target": "codamosa-escaping-coverage-2023"
     },
     {
       "source": "benchmarking-llms-unit-2025",
       "target": "bigcodebench-2024"
     },
     {
       "source": "benchmarking-llms-unit-2025",
       "target": "llms-se-systematic-review-2023"
     },
     {
       "source": "benchmarking-llms-unit-2025",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "benchmarking-llms-unit-2025",
       "target": "largescale-independent-comprehensive-2024"
     },
     {
       "source": "benchmarks-automated-commonsense-2023",
       "target": "beyond-imitation-game-2022"
     },
     {
       "source": "bert-pretraining-deep-2018",
       "target": "attention-is-all-you-need-2017"
     },
     {
       "source": "best-practices-ai-2023",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "beyond-automation-job-redesign-2025",
       "target": "experimental-evidence-productivity-2023"
     },
     {
       "source": "beyond-automation-job-redesign-2025",
       "target": "generative-ai-at-2023"
     },
     {
       "source": "beyond-automation-job-redesign-2025",
       "target": "canaries-coal-mine-2025"
     },
     {
       "source": "beyond-benchmark-innovative-2025",
       "target": "formalizing-benchmarking-prompt-2023"
     },
     {
       "source": "beyond-benchmark-innovative-2025",
       "target": "automatic-universal-prompt-2024"
     },
     {
       "source": "beyond-benchmark-innovative-2025",
       "target": "ai-scientist-fully-2024"
     },
     {
       "source": "beyond-chinchillaoptimal-accounting-2023",
       "target": "chinchilla-compute-optimal-2022"
     },
     {
       "source": "beyond-chinchillaoptimal-accounting-2023",
       "target": "scaling-laws-2020"
     },
     {
       "source": "beyond-chinchillaoptimal-accounting-2023",
       "target": "llama-open-efficient-2023"
     },
     {
       "source": "beyond-chunks-graphs-2025",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "beyond-commit-developer-perspectives-2026",
       "target": "copilot-productivity-controlled-2023"
     },
     {
       "source": "beyond-commit-developer-perspectives-2026",
       "target": "code-me-me-2025"
     },
     {
       "source": "beyond-correctness-benchmarking-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "beyond-correctness-benchmarking-2024",
       "target": "your-code-generated-2023"
     },
     {
       "source": "beyond-correctness-benchmarking-2024",
       "target": "livecodebench-2024"
     },
     {
       "source": "beyond-correctness-benchmarking-2024",
       "target": "quantifying-contamination-evaluating-2024"
     },
     {
       "source": "beyond-correctness-benchmarking-2024",
       "target": "classeval-manuallycrafted-benchmark-2023"
     },
     {
       "source": "beyond-correctness-benchmarking-2024",
       "target": "deepseek-coder-2024"
     },
     {
       "source": "beyond-correctness-benchmarking-2024",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "beyond-correctness-benchmarking-2024",
       "target": "code-llama-2023"
     },
     {
       "source": "beyond-correctness-benchmarking-2024",
       "target": "wizardcoder-empowering-code-2023"
     },
     {
       "source": "beyond-correctness-rewarding-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "beyond-functional-correctness-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "beyond-functional-correctness-2024",
       "target": "codemirage-hallucinations-code-2024"
     },
     {
       "source": "beyond-functional-correctness-2024",
       "target": "collubench-benchmark-predicting-2024"
     },
     {
       "source": "beyond-functional-correctness-2024",
       "target": "llm-hallucinations-code-practical-2024"
     },
     {
       "source": "beyond-functional-correctness-2024",
       "target": "what-wrong-your-2024"
     },
     {
       "source": "beyond-functional-correctness-2024",
       "target": "bugs-large-language-2024"
     },
     {
       "source": "beyond-functional-correctness-2024",
       "target": "your-code-generated-2023"
     },
     {
       "source": "beyond-functional-correctness-2024",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "beyond-functional-correctness-2024",
       "target": "survey-hallucination-large-2023-2"
     },
     {
       "source": "beyond-hype-comprehensive-2024",
       "target": "how-far-we-2023"
     },
     {
       "source": "beyond-hype-comprehensive-2024",
       "target": "how-beginning-programmers-2024"
     },
     {
       "source": "beyond-imitation-game-2022",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "beyond-imitation-game-2022",
       "target": "palm-scaling-language-2022"
     },
     {
       "source": "beyond-imitation-game-2022",
       "target": "scaling-laws-2020"
     },
     {
       "source": "beyond-imitation-game-2022",
       "target": "mmlu-measuring-massive-2020"
     },
     {
       "source": "beyond-imitation-game-2022",
       "target": "chinchilla-compute-optimal-2022"
     },
     {
       "source": "beyond-imitation-game-2022",
       "target": "lamda-language-models-2022"
     },
     {
       "source": "beyond-mimicry-preference-2025",
       "target": "emergent-abilities-mirage-2023"
     },
     {
       "source": "beyond-mimicry-preference-2025",
       "target": "alignment-faking-2024"
     },
     {
       "source": "beyond-promptinduced-lies-2025",
       "target": "alignment-faking-2024"
     },
     {
       "source": "beyond-promptinduced-lies-2025",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "beyond-quantity-trajectory-2026",
       "target": "gorilla-large-language-2023"
     },
     {
       "source": "beyond-quantity-trajectory-2026",
       "target": "toolllm-facilitating-large-2023"
     },
     {
       "source": "beyond-quantity-trajectory-2026",
       "target": "swerebench-automated-pipeline-2025"
     },
     {
       "source": "beyond-quantity-trajectory-2026",
       "target": "livecodebench-2024"
     },
     {
       "source": "beyond-quantity-trajectory-2026",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "beyond-quantity-trajectory-2026",
       "target": "toolformer-language-models-2023"
     },
     {
       "source": "beyond-quantity-trajectory-2026",
       "target": "survey-code-gen-llm-agents-2025"
     },
     {
       "source": "beyond-singleagent-safety-2025",
       "target": "uc-berkeley-mast-2025"
     },
     {
       "source": "beyond-singleagent-safety-2025",
       "target": "multiagent-risks-from-2025"
     },
     {
       "source": "beyond-singleagent-safety-2025",
       "target": "autogen-multi-agent-2023"
     },
     {
       "source": "beyond-singleagent-safety-2025",
       "target": "swe-agent-2024"
     },
     {
       "source": "beyond-singleagent-safety-2025",
       "target": "voyager-open-ended-2023"
     },
     {
       "source": "beyond-static-datasets-2023",
       "target": "palm-scaling-language-2022"
     },
     {
       "source": "beyond-static-datasets-2023",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "beyond-static-datasets-2023",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "beyond-static-pattern-2025",
       "target": "automated-program-repair-2023"
     },
     {
       "source": "beyond-static-pattern-2025",
       "target": "your-code-generated-2023"
     },
     {
       "source": "beyond-synthetic-benchmarks-2025",
       "target": "classeval-manuallycrafted-benchmark-2023"
     },
     {
       "source": "beyond-synthetic-benchmarks-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "beyond-synthetic-benchmarks-2025",
       "target": "your-code-generated-2023"
     },
     {
       "source": "beyond-synthetic-benchmarks-2025",
       "target": "graphcodeagent-dual-graphguided-2025"
     },
     {
       "source": "beyond-synthetic-benchmarks-2025",
       "target": "retrievalaugmented-code-generation-2025"
     },
     {
       "source": "beyond-synthetic-benchmarks-2025",
       "target": "bugs-large-language-2024"
     },
     {
       "source": "beyond-synthetic-benchmarks-2025",
       "target": "coderagbench-can-retrieval-2024"
     },
     {
       "source": "beyond-synthetic-benchmarks-2025",
       "target": "survey-llm-code-generation-2025"
     },
     {
       "source": "beyond-synthetic-benchmarks-2025",
       "target": "repairagent-llm-bug-repair-2024"
     },
     {
       "source": "beyond-textual-context-2025",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "beyond-token-probes-2025",
       "target": "selfcheckgpt-zeroresource-blackbox-2023"
     },
     {
       "source": "bias-assessment-mitigation-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "bias-assessment-mitigation-2023",
       "target": "swe-bench-2023"
     },
     {
       "source": "bias-assessment-mitigation-2023",
       "target": "your-code-generated-2023"
     },
     {
       "source": "bias-assessment-mitigation-2023",
       "target": "codamosa-escaping-coverage-2023"
     },
     {
       "source": "bias-unveiled-investigating-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "bias-unveiled-investigating-2024",
       "target": "starcoder-2023"
     },
     {
       "source": "bias-unveiled-investigating-2024",
       "target": "code-llama-2023"
     },
     {
       "source": "biasalert-plugandplay-tool-2024",
       "target": "beavertails-improved-safety-2023"
     },
     {
       "source": "biasalert-plugandplay-tool-2024",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "bigcodebench-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "bigcodebench-2024",
       "target": "swe-bench-2023"
     },
     {
       "source": "bigcodebench-2024",
       "target": "livecodebench-2024"
     },
     {
       "source": "bigcodebench-2024",
       "target": "your-code-generated-2023"
     },
     {
       "source": "bigcodebench-2024",
       "target": "code-llama-2023"
     },
     {
       "source": "bigcodebench-2024",
       "target": "starcoder2-2024"
     },
     {
       "source": "bigcodebench-2024",
       "target": "swe-agent-2024"
     },
     {
       "source": "bigrpo-bidirectional-optimization-2025",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "bigrpo-bidirectional-optimization-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "bigrpo-bidirectional-optimization-2025",
       "target": "survey-large-language-2023"
     },
     {
       "source": "bioplanner-automatic-evaluation-2023",
       "target": "voyager-open-ended-2023"
     },
     {
       "source": "bioplanner-automatic-evaluation-2023",
       "target": "sparks-agi-early-2023"
     },
     {
       "source": "bioplanner-automatic-evaluation-2023",
       "target": "toolformer-language-models-2023"
     },
     {
       "source": "bioplanner-automatic-evaluation-2023",
       "target": "tree-thoughts-deliberate-2023"
     },
     {
       "source": "bioplanner-automatic-evaluation-2023",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "bioragent-retrievalaugmented-generation-2024",
       "target": "gemini-15-technical-report-2024"
     },
     {
       "source": "biotrouble-multiagent-workflow-2026",
       "target": "survey-autonomous-llm-agents-2023"
     },
     {
       "source": "biotrouble-multiagent-workflow-2026",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "biotrouble-multiagent-workflow-2026",
       "target": "rise-potential-large-2023"
     },
     {
       "source": "bitsaicr-automated-code-2025",
       "target": "aiassisted-assessment-coding-2024"
     },
     {
       "source": "bitsaicr-automated-code-2025",
       "target": "aipowered-code-review-2024"
     },
     {
       "source": "bitsaicr-automated-code-2025",
       "target": "llm-critics-help-2024"
     },
     {
       "source": "bitsaicr-automated-code-2025",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "blockdialect-blockwise-finegrained-2025",
       "target": "smoothquant-accurate-efficient-2022"
     },
     {
       "source": "boosting-llm-reasoning-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "boosting-llm-reasoning-2025",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "boosting-llm-reasoning-2025",
       "target": "autogen-multi-agent-2023"
     },
     {
       "source": "boosting-redundancybased-automated-2023",
       "target": "less-training-more-2022"
     },
     {
       "source": "boosting-redundancybased-automated-2023",
       "target": "copiloting-copilots-fusing-2023"
     },
     {
       "source": "boosting-redundancybased-automated-2023",
       "target": "gamma-revisiting-templatebased-2023"
     },
     {
       "source": "boosting-redundancybased-automated-2023",
       "target": "impact-code-language-2023"
     },
     {
       "source": "boosting-redundancybased-automated-2023",
       "target": "automated-program-repair-2022"
     },
     {
       "source": "boosting-redundancybased-automated-2023",
       "target": "systematic-literature-review-2024"
     },
     {
       "source": "boosting-redundancybased-automated-2023",
       "target": "hybrid-automated-program-2024"
     },
     {
       "source": "bottomup-domainspecific-superintelligence-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "bottomup-domainspecific-superintelligence-2025",
       "target": "compute-optimal-inference-2024"
     },
     {
       "source": "bottomup-domainspecific-superintelligence-2025",
       "target": "emergent-abilities-large-2022"
     },
     {
       "source": "bottomup-domainspecific-superintelligence-2025",
       "target": "emergent-abilities-mirage-2023"
     },
     {
       "source": "bottomup-domainspecific-superintelligence-2025",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "bpo-staying-close-2024",
       "target": "gemma-open-models-2024"
     },
     {
       "source": "break-sequential-dependency-2024",
       "target": "accelerating-large-language-2023"
     },
     {
       "source": "break-sequential-dependency-2024",
       "target": "fast-inference-from-2022"
     },
     {
       "source": "break-sequential-dependency-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "break-sequential-dependency-2024",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "breaking-prompt-wall-2025",
       "target": "jailbreaking-safety-aligned-llms-2024"
     },
     {
       "source": "breaking-prompt-wall-2025",
       "target": "not-what-youve-2023"
     },
     {
       "source": "bridging-human-interpretation-2026",
       "target": "uc-berkeley-mast-2025"
     },
     {
       "source": "bridging-human-interpretation-2026",
       "target": "autogen-multi-agent-2023"
     },
     {
       "source": "bridging-human-interpretation-2026",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "bridging-human-interpretation-2026",
       "target": "chatdev-communicative-agents-2023"
     },
     {
       "source": "bridging-human-interpretation-2026",
       "target": "measuring-agents-production-2025"
     },
     {
       "source": "bridging-human-interpretation-2026",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "bridging-llmgenerated-code-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "bridging-llmgenerated-code-2025",
       "target": "codejudge-evaluating-code-2024"
     },
     {
       "source": "broken-neural-scaling-2022",
       "target": "scaling-laws-2020"
     },
     {
       "source": "broken-neural-scaling-2022",
       "target": "emergent-abilities-large-2022"
     },
     {
       "source": "broken-neural-scaling-2022",
       "target": "beyond-imitation-game-2022"
     },
     {
       "source": "broken-neural-scaling-2022",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "broken-neural-scaling-2022",
       "target": "grokking-generalization-beyond-2022"
     },
     {
       "source": "broken-neural-scaling-2022",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "browserarena-web-agents-2025",
       "target": "chatbot-arena-open-2024"
     },
     {
       "source": "browserarena-web-agents-2025",
       "target": "webarena-autonomous-agents-2023"
     },
     {
       "source": "browserarena-web-agents-2025",
       "target": "visualwebarena-evaluating-multimodal-2024"
     },
     {
       "source": "browserarena-web-agents-2025",
       "target": "openhands-ai-sw-agent-2024"
     },
     {
       "source": "browserarena-web-agents-2025",
       "target": "copilot-arena-platform-2025"
     },
     {
       "source": "browserarena-web-agents-2025",
       "target": "osworld-benchmarking-multimodal-2024"
     },
     {
       "source": "browsesafe-understanding-preventing-2025",
       "target": "agent-security-bench-2024"
     },
     {
       "source": "browsesafe-understanding-preventing-2025",
       "target": "wasp-benchmarking-web-2025"
     },
     {
       "source": "browsesafe-understanding-preventing-2025",
       "target": "formalizing-benchmarking-prompt-2023"
     },
     {
       "source": "browsesafe-understanding-preventing-2025",
       "target": "adaptive-attacks-bypass-defenses-2025"
     },
     {
       "source": "budgetaware-agentic-routing-2026",
       "target": "appworld-controllable-world-2024"
     },
     {
       "source": "bugdar-aiaugmented-secure-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "bugdar-aiaugmented-secure-2025",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "bugs-large-language-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "bugs-large-language-2024",
       "target": "your-code-generated-2023"
     },
     {
       "source": "bugs-large-language-2024",
       "target": "lost-translation-study-2024"
     },
     {
       "source": "bugs-large-language-2024",
       "target": "adaptive-test-generation-2023"
     },
     {
       "source": "bugs-large-language-2024",
       "target": "codamosa-escaping-coverage-2023"
     },
     {
       "source": "build-your-personalized-2025",
       "target": "ai-scientist-fully-2024"
     },
     {
       "source": "build-your-personalized-2025",
       "target": "ai-scientistv2-workshoplevel-2025"
     },
     {
       "source": "build-your-personalized-2025",
       "target": "uc-berkeley-mast-2025"
     },
     {
       "source": "build-your-personalized-2025",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "build-your-personalized-2025",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "build-your-personalized-2025",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "build-your-personalized-2025",
       "target": "adas-automated-design-2024"
     },
     {
       "source": "build-your-personalized-2025",
       "target": "lhdeception-simulating-understanding-2025"
     },
     {
       "source": "build-your-personalized-2025",
       "target": "large-language-model-2024"
     },
     {
       "source": "building-coding-assistant-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "building-coding-assistant-2024",
       "target": "reacc-retrievalaugmented-code-2022"
     },
     {
       "source": "building-coding-assistant-2024",
       "target": "codebert-pretrained-model-2020"
     },
     {
       "source": "building-cooperative-embodied-2023",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "building-cooperative-embodied-2023",
       "target": "generative-agents-interactive-2023"
     },
     {
       "source": "building-cooperative-embodied-2023",
       "target": "voyager-open-ended-2023"
     },
     {
       "source": "building-cooperative-embodied-2023",
       "target": "improving-factuality-reasoning-2023"
     },
     {
       "source": "building-cooperative-embodied-2023",
       "target": "camel-communicative-agents-2023"
     },
     {
       "source": "building-cooperative-embodied-2023",
       "target": "sparks-agi-early-2023"
     },
     {
       "source": "building-cooperative-embodied-2023",
       "target": "survey-autonomous-llm-agents-2023"
     },
     {
       "source": "building-cooperative-embodied-2023",
       "target": "rise-potential-large-2023"
     },
     {
       "source": "building-understandable-messaging-2024",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "building-understandable-messaging-2024",
       "target": "rise-potential-large-2023"
     },
     {
       "source": "building-understandable-messaging-2024",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "bypassing-llm-guardrails-2025",
       "target": "automatic-universal-prompt-2024"
     },
     {
       "source": "bypassing-llm-guardrails-2025",
       "target": "llama-3-herd-2024"
     },
     {
       "source": "bypassing-llm-guardrails-2025",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "bytesized32refactored-extensible-interactive-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "bytesized32refactored-extensible-interactive-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "bytesized32refactored-extensible-interactive-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "bytesized32refactored-extensible-interactive-2025",
       "target": "bigcodebench-2024"
     },
     {
       "source": "bytesized32refactored-extensible-interactive-2025",
       "target": "survey-code-gen-llm-agents-2025"
     },
     {
       "source": "bytesized32refactored-extensible-interactive-2025",
       "target": "survey-llm-code-generation-2025"
     },
     {
       "source": "c3po-optimized-large-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "c3po-optimized-large-2025",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "c3po-optimized-large-2025",
       "target": "selfconsistency-improves-chain-2022"
     },
     {
       "source": "cacheprune-neuralbased-attribution-2025",
       "target": "not-what-youve-2023"
     },
     {
       "source": "cacheprune-neuralbased-attribution-2025",
       "target": "secalign-defending-against-2024"
     },
     {
       "source": "cacheprune-neuralbased-attribution-2025",
       "target": "defending-against-indirect-2024"
     },
     {
       "source": "cacheprune-neuralbased-attribution-2025",
       "target": "fath-authenticationbased-testtime-2024"
     },
     {
       "source": "cacheprune-neuralbased-attribution-2025",
       "target": "task-shield-enforcing-2024"
     },
     {
       "source": "cacheprune-neuralbased-attribution-2025",
       "target": "jatmo-prompt-injection-2023"
     },
     {
       "source": "cacheprune-neuralbased-attribution-2025",
       "target": "automatic-universal-prompt-2024"
     },
     {
       "source": "calibrating-llm-judges-2025",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "calibrating-llm-judges-2025",
       "target": "selfconsistency-improves-chain-2022"
     },
     {
       "source": "calibration-large-language-2026",
       "target": "selfconsistency-improves-chain-2022"
     },
     {
       "source": "calibration-large-language-2026",
       "target": "compute-optimal-inference-2024"
     },
     {
       "source": "calibration-large-language-2026",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "camel-communicative-agents-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "camel-communicative-agents-2023",
       "target": "your-code-generated-2023"
     },
     {
       "source": "camel-communicative-agents-2023",
       "target": "llama-open-efficient-2023"
     },
     {
       "source": "camel-communicative-agents-2023",
       "target": "self-instruct-aligning-language-2022"
     },
     {
       "source": "camel-communicative-agents-2023",
       "target": "toolformer-language-models-2023"
     },
     {
       "source": "camel-communicative-agents-2023",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "camel-communicative-agents-2023",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "camel-communicative-agents-2023",
       "target": "constitutional-ai-2022"
     },
     {
       "source": "camel-communicative-agents-2023",
       "target": "webarena-autonomous-agents-2023"
     },
     {
       "source": "can-1b-llm-2025",
       "target": "compute-optimal-inference-2024"
     },
     {
       "source": "can-1b-llm-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "can-1b-llm-2025",
       "target": "inference-scaling-laws-2024"
     },
     {
       "source": "can-1b-llm-2025",
       "target": "selfconsistency-improves-chain-2022"
     },
     {
       "source": "can-chatgpt-support-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "can-chatgpt-support-2024",
       "target": "your-code-generated-2023"
     },
     {
       "source": "can-chatgpt-support-2024",
       "target": "can-llm-replace-2023"
     },
     {
       "source": "can-indirect-prompt-2025",
       "target": "not-what-youve-2023"
     },
     {
       "source": "can-indirect-prompt-2025",
       "target": "defending-against-indirect-2024"
     },
     {
       "source": "can-indirect-prompt-2025",
       "target": "automatic-universal-prompt-2024"
     },
     {
       "source": "can-indirect-prompt-2025",
       "target": "formalizing-benchmarking-prompt-2023"
     },
     {
       "source": "can-indirect-prompt-2025",
       "target": "jatmo-prompt-injection-2023"
     },
     {
       "source": "can-indirect-prompt-2025",
       "target": "prompt-injection-llm-apps-2023"
     },
     {
       "source": "can-large-language-2025",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "can-llm-replace-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "can-llm-replace-2023",
       "target": "swe-bench-2023"
     },
     {
       "source": "can-llm-replace-2023",
       "target": "your-code-generated-2023"
     },
     {
       "source": "can-llm-replace-2023",
       "target": "gorilla-large-language-2023"
     },
     {
       "source": "can-llms-replace-2025",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "can-llms-replace-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "can-llms-replace-2025",
       "target": "deepseek-coder-v2-2024"
     },
     {
       "source": "can-llms-replace-2025",
       "target": "llms-se-systematic-review-2023"
     },
     {
       "source": "can-llms-replace-2025",
       "target": "compute-optimal-inference-2024"
     },
     {
       "source": "can-reasoning-models-2025",
       "target": "alignment-faking-2024"
     },
     {
       "source": "can-reasoning-models-2025",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "can-vibe-coding-2025",
       "target": "metr-rct-2025"
     },
     {
       "source": "can-vibe-coding-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "can-vibe-coding-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "can-vibe-coding-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "can-vibe-coding-2025",
       "target": "survey-llm-code-generation-2025"
     },
     {
       "source": "can-vibe-coding-2025",
       "target": "alphacode-competition-level-2022"
     },
     {
       "source": "can-vibe-coding-2025",
       "target": "bigcodebench-2024"
     },
     {
       "source": "can-vibe-coding-2025",
       "target": "swe-bench-pro-2025"
     },
     {
       "source": "canaries-coal-mine-2025",
       "target": "generative-ai-at-2023"
     },
     {
       "source": "canaries-coal-mine-2025",
       "target": "copilot-productivity-controlled-2023"
     },
     {
       "source": "capability-ceilings-autoregressive-2025",
       "target": "scaling-laws-2020"
     },
     {
       "source": "capability-ceilings-autoregressive-2025",
       "target": "chinchilla-compute-optimal-2022"
     },
     {
       "source": "capability-ceilings-autoregressive-2025",
       "target": "mmlu-measuring-massive-2020"
     },
     {
       "source": "capability-ceilings-autoregressive-2025",
       "target": "emergent-abilities-large-2022"
     },
     {
       "source": "capability-ceilings-autoregressive-2025",
       "target": "emergent-abilities-mirage-2023"
     },
     {
       "source": "capabilityoriented-training-induced-2026",
       "target": "alignment-faking-2024"
     },
     {
       "source": "capabilityoriented-training-induced-2026",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "capabilityoriented-training-induced-2026",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "capabilityoriented-training-induced-2026",
       "target": "livecodebench-2024"
     },
     {
       "source": "capture-contextaware-prompt-2025",
       "target": "not-what-youve-2023"
     },
     {
       "source": "capture-contextaware-prompt-2025",
       "target": "formalizing-benchmarking-prompt-2023"
     },
     {
       "source": "capture-contextaware-prompt-2025",
       "target": "injecguard-benchmarking-mitigating-2024"
     },
     {
       "source": "capture-contextaware-prompt-2025",
       "target": "prompt-injection-llm-apps-2023"
     },
     {
       "source": "capture-contextaware-prompt-2025",
       "target": "jatmo-prompt-injection-2023"
     },
     {
       "source": "carbon-footprint-evaluation-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "carbon-footprint-evaluation-2025",
       "target": "learn-code-sustainably-2024"
     },
     {
       "source": "carbon-footprint-evaluation-2025",
       "target": "your-code-generated-2023"
     },
     {
       "source": "carbon-footprint-evaluation-2025",
       "target": "scaffolded-model-capability-2023"
     },
     {
       "source": "caredio-cultural-alignment-2025",
       "target": "unintended-impacts-llm-2024"
     },
     {
       "source": "case-4bit-precision-2022",
       "target": "smoothquant-accurate-efficient-2022"
     },
     {
       "source": "case-4bit-precision-2022",
       "target": "scaling-laws-2020"
     },
     {
       "source": "case-study-transformative-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "case-study-transformative-2025",
       "target": "no-need-lift-2023"
     },
     {
       "source": "case-study-transformative-2025",
       "target": "performance-study-llmgenerated-2024"
     },
     {
       "source": "case-study-transformative-2025",
       "target": "your-code-generated-2023"
     },
     {
       "source": "cast-enhancing-code-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "cast-enhancing-code-2025",
       "target": "coderagbench-can-retrieval-2024"
     },
     {
       "source": "cast-enhancing-code-2025",
       "target": "agentless-2024"
     },
     {
       "source": "cast-enhancing-code-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "cast-enhancing-code-2025",
       "target": "starcoder2-2024"
     },
     {
       "source": "cast-enhancing-code-2025",
       "target": "code-llama-2023"
     },
     {
       "source": "cast-enhancing-code-2025",
       "target": "codegrag-bridging-gap-2024"
     },
     {
       "source": "cast-enhancing-code-2025",
       "target": "repocoder-repositorylevel-code-2023"
     },
     {
       "source": "caster-breaking-costperformance-2026",
       "target": "scaffolded-model-capability-2023"
     },
     {
       "source": "caster-breaking-costperformance-2026",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "caster-breaking-costperformance-2026",
       "target": "swe-agent-2024"
     },
     {
       "source": "caster-breaking-costperformance-2026",
       "target": "chatdev-communicative-agents-2023"
     },
     {
       "source": "catarena-evaluating-evolutionary-2025",
       "target": "swe-agent-2024"
     },
     {
       "source": "catarena-evaluating-evolutionary-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "catarena-evaluating-evolutionary-2025",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "catarena-evaluating-evolutionary-2025",
       "target": "redcode-risky-code-2024"
     },
     {
       "source": "catarena-evaluating-evolutionary-2025",
       "target": "survey-code-gen-llm-agents-2025"
     },
     {
       "source": "catch-me-if-2025",
       "target": "constitutional-ai-2022"
     },
     {
       "source": "catch-me-if-2025",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "catch-me-if-2025",
       "target": "preventing-rogue-agents-2025"
     },
     {
       "source": "catch-me-if-2025",
       "target": "llm-strategic-deception-under-pressure-2023"
     },
     {
       "source": "catdb-datacatalogguided-llmbased-2025",
       "target": "autogen-multi-agent-2023"
     },
     {
       "source": "causalarmor-efficient-indirect-2026",
       "target": "drift-dynamic-rulebased-2025"
     },
     {
       "source": "causalarmor-efficient-indirect-2026",
       "target": "melon-provable-defense-2025"
     },
     {
       "source": "causalarmor-efficient-indirect-2026",
       "target": "promptarmor-simple-yet-2025"
     },
     {
       "source": "causalarmor-efficient-indirect-2026",
       "target": "adaptive-attacks-bypass-defenses-2025"
     },
     {
       "source": "causalarmor-efficient-indirect-2026",
       "target": "indirect-prompt-injections-2025"
     },
     {
       "source": "causalarmor-efficient-indirect-2026",
       "target": "agent-security-bench-2024"
     },
     {
       "source": "cbfllm-safe-control-2024",
       "target": "constitutional-ai-2022"
     },
     {
       "source": "cbfllm-safe-control-2024",
       "target": "llama-3-herd-2024"
     },
     {
       "source": "cctest-testing-repairing-2022",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "cctest-testing-repairing-2022",
       "target": "alphacode-competition-level-2022"
     },
     {
       "source": "cctest-testing-repairing-2022",
       "target": "codebert-pretrained-model-2020"
     },
     {
       "source": "chain-of-thought-prompting-2022",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "chain-of-thought-prompting-2022",
       "target": "selfconsistency-improves-chain-2022"
     },
     {
       "source": "chain-of-thought-prompting-2022",
       "target": "emergent-abilities-large-2022"
     },
     {
       "source": "chain-of-thought-prompting-2022",
       "target": "lamda-language-models-2022"
     },
     {
       "source": "chainofthought-prompting-obscures-2025",
       "target": "selfcheckgpt-zeroresource-blackbox-2023"
     },
     {
       "source": "chainofthought-prompting-obscures-2025",
       "target": "incontext-sharpness-as-2024"
     },
     {
       "source": "chainofthought-prompting-obscures-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "chainofthought-prompting-obscures-2025",
       "target": "unsupervised-realtime-hallucination-2024"
     },
     {
       "source": "chainpoll-high-efficacy-2023",
       "target": "selfcheckgpt-zeroresource-blackbox-2023"
     },
     {
       "source": "chainpoll-high-efficacy-2023",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "challenge-optimization-context-2025",
       "target": "codefill-multitoken-code-2022"
     },
     {
       "source": "challenge-optimization-context-2025",
       "target": "repocoder-repositorylevel-code-2023"
     },
     {
       "source": "challenge-optimization-context-2025",
       "target": "code-llama-2023"
     },
     {
       "source": "challenge-optimization-context-2025",
       "target": "repoformer-selective-retrieval-2024"
     },
     {
       "source": "challenge-optimization-context-2025",
       "target": "rlcoder-reinforcement-learning-2024"
     },
     {
       "source": "challenge-optimization-context-2025",
       "target": "qwen25coder-technical-report-2024"
     },
     {
       "source": "challenges-humanagent-communication-2024",
       "target": "autogen-multi-agent-2023"
     },
     {
       "source": "challenges-humanagent-communication-2024",
       "target": "magenticone-generalist-multiagent-2024"
     },
     {
       "source": "challenges-humanagent-communication-2024",
       "target": "openhands-ai-sw-agent-2024"
     },
     {
       "source": "challenges-paths-ai-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "challenges-paths-ai-2025",
       "target": "swe-agent-2024"
     },
     {
       "source": "challenges-paths-ai-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "challenges-paths-ai-2025",
       "target": "copilot-arena-platform-2025"
     },
     {
       "source": "challenges-paths-ai-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "challenges-paths-ai-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "challenges-paths-ai-2025",
       "target": "agentless-2024"
     },
     {
       "source": "challenges-paths-ai-2025",
       "target": "openhands-ai-sw-agent-2024"
     },
     {
       "source": "changes-coding-behavior-2026",
       "target": "metr-rct-2025"
     },
     {
       "source": "changes-coding-behavior-2026",
       "target": "empirical-study-usage-2024"
     },
     {
       "source": "characterizing-llm-inference-2025",
       "target": "scaffolded-model-capability-2023"
     },
     {
       "source": "characterizing-llm-inference-2025",
       "target": "sloaware-gpu-dvfs-2024"
     },
     {
       "source": "chasing-progress-not-2024",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "chat-bankmanfried-exploration-2024",
       "target": "llm-strategic-deception-under-pressure-2023"
     },
     {
       "source": "chatassert-llmbased-test-2025",
       "target": "codamosa-escaping-coverage-2023"
     },
     {
       "source": "chatassert-llmbased-test-2025",
       "target": "automated-program-repair-2023"
     },
     {
       "source": "chatassert-llmbased-test-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "chatassert-llmbased-test-2025",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "chatassert-llmbased-test-2025",
       "target": "less-training-more-2022"
     },
     {
       "source": "chatbot-arena-open-2024",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "chatbot-arena-open-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "chatbot-arena-open-2024",
       "target": "rethinking-benchmark-contamination-2023"
     },
     {
       "source": "chatbot-arena-open-2024",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "chatdev-communicative-agents-2023",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "chatdev-communicative-agents-2023",
       "target": "generative-agents-interactive-2023"
     },
     {
       "source": "chatdev-communicative-agents-2023",
       "target": "voyager-open-ended-2023"
     },
     {
       "source": "chatdev-communicative-agents-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "chatdev-communicative-agents-2023",
       "target": "toolllm-facilitating-large-2023"
     },
     {
       "source": "chatdev-communicative-agents-2023",
       "target": "chateval-better-llmbased-2023"
     },
     {
       "source": "chatdev-communicative-agents-2023",
       "target": "webarena-autonomous-agents-2023"
     },
     {
       "source": "chateval-better-llmbased-2023",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "chateval-better-llmbased-2023",
       "target": "improving-factuality-reasoning-2023"
     },
     {
       "source": "chateval-better-llmbased-2023",
       "target": "camel-communicative-agents-2023"
     },
     {
       "source": "chateval-better-llmbased-2023",
       "target": "chatdev-communicative-agents-2023"
     },
     {
       "source": "chateval-better-llmbased-2023",
       "target": "generative-agents-interactive-2023"
     },
     {
       "source": "chatgpt-agent-system-2025",
       "target": "building-early-warning-2024"
     },
     {
       "source": "chatgpt-agent-system-2025",
       "target": "paperbench-evaluating-ais-2025"
     },
     {
       "source": "chatgpt-not-all-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "chatgpt-not-all-2023",
       "target": "alphacode-competition-level-2022"
     },
     {
       "source": "chatgpt-not-all-2023",
       "target": "lamda-language-models-2022"
     },
     {
       "source": "chatinject-abusing-chat-2025",
       "target": "adaptive-attacks-break-2025"
     },
     {
       "source": "chatinject-abusing-chat-2025",
       "target": "not-what-youve-2023"
     },
     {
       "source": "chatinject-abusing-chat-2025",
       "target": "secalign-defending-against-2024"
     },
     {
       "source": "chatinject-abusing-chat-2025",
       "target": "agent-security-bench-2024"
     },
     {
       "source": "chatinject-abusing-chat-2025",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "chatinject-abusing-chat-2025",
       "target": "defending-against-indirect-2024"
     },
     {
       "source": "chatofthought-collaborative-multiagent-2025",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "chatofthought-collaborative-multiagent-2025",
       "target": "generative-agents-interactive-2023"
     },
     {
       "source": "chatofthought-collaborative-multiagent-2025",
       "target": "autogen-multi-agent-2023"
     },
     {
       "source": "chatofthought-collaborative-multiagent-2025",
       "target": "llama-open-efficient-2023"
     },
     {
       "source": "chatunitest-framework-llmbased-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "chatunitest-framework-llmbased-2023",
       "target": "adaptive-test-generation-2023"
     },
     {
       "source": "chatunitest-framework-llmbased-2023",
       "target": "no-more-manual-2023"
     },
     {
       "source": "chatunitest-framework-llmbased-2023",
       "target": "code-llama-2023"
     },
     {
       "source": "chatunitest-framework-llmbased-2023",
       "target": "coverup-effective-high-2024"
     },
     {
       "source": "chatunitest-framework-llmbased-2023",
       "target": "codeaware-prompting-study-2024"
     },
     {
       "source": "chatunitest-framework-llmbased-2023",
       "target": "lost-middle-how-2023"
     },
     {
       "source": "check-your-facts-2023",
       "target": "toolformer-language-models-2023"
     },
     {
       "source": "checkpointgcg-auditing-attacking-2025",
       "target": "secalign-defending-against-2024"
     },
     {
       "source": "checkpointgcg-auditing-attacking-2025",
       "target": "not-what-youve-2023"
     },
     {
       "source": "chinchilla-compute-optimal-2022",
       "target": "scaling-laws-2020"
     },
     {
       "source": "chinchilla-compute-optimal-2022",
       "target": "mmlu-measuring-massive-2020"
     },
     {
       "source": "chinchilla-compute-optimal-2022",
       "target": "unified-scaling-laws-2022"
     },
     {
       "source": "chipbench-nextstep-benchmark-2026",
       "target": "verilogeval-evaluating-large-2023"
     },
     {
       "source": "chipbench-nextstep-benchmark-2026",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "chipbench-nextstep-benchmark-2026",
       "target": "survey-code-gen-llm-agents-2025"
     },
     {
       "source": "chopchop-programmable-framework-2025",
       "target": "monitorguided-decoding-code-2023"
     },
     {
       "source": "chopchop-programmable-framework-2025",
       "target": "syncode-llm-generation-2024"
     },
     {
       "source": "chopchop-programmable-framework-2025",
       "target": "efficient-guided-generation-2023"
     },
     {
       "source": "chorus-zeroshot-hierarchical-2025",
       "target": "llama-3-herd-2024"
     },
     {
       "source": "chorus-zeroshot-hierarchical-2025",
       "target": "phi4-technical-report-2024"
     },
     {
       "source": "chorus-zeroshot-hierarchical-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "chorus-zeroshot-hierarchical-2025",
       "target": "qwen25coder-technical-report-2024"
     },
     {
       "source": "chorus-zeroshot-hierarchical-2025",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "chorus-zeroshot-hierarchical-2025",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "ciata-risk-assessment-2025",
       "target": "not-what-youve-2023"
     },
     {
       "source": "ciata-risk-assessment-2025",
       "target": "prompt-injection-llm-apps-2023"
     },
     {
       "source": "ciata-risk-assessment-2025",
       "target": "automatic-universal-prompt-2024"
     },
     {
       "source": "ciata-risk-assessment-2025",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "ciata-risk-assessment-2025",
       "target": "constitutional-ai-2022"
     },
     {
       "source": "cigar-costefficient-program-2024",
       "target": "automated-program-repair-2023"
     },
     {
       "source": "cigar-costefficient-program-2024",
       "target": "impact-code-language-2023"
     },
     {
       "source": "cigar-costefficient-program-2024",
       "target": "scaffolded-model-capability-2023"
     },
     {
       "source": "cigar-costefficient-program-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "cigar-costefficient-program-2024",
       "target": "automated-program-repair-2022"
     },
     {
       "source": "cigar-costefficient-program-2024",
       "target": "critical-review-large-2023"
     },
     {
       "source": "citationenhanced-generation-llmbased-2024",
       "target": "selfcheckgpt-zeroresource-blackbox-2023"
     },
     {
       "source": "citationenhanced-generation-llmbased-2024",
       "target": "sirens-song-ai-2023"
     },
     {
       "source": "citationenhanced-generation-llmbased-2024",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "citationgrounded-code-comprehension-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "citationgrounded-code-comprehension-2025",
       "target": "codebert-pretrained-model-2020"
     },
     {
       "source": "citationgrounded-code-comprehension-2025",
       "target": "code-llama-2023"
     },
     {
       "source": "citywalk-enhancing-llmbased-2025",
       "target": "chatunitest-framework-llmbased-2023"
     },
     {
       "source": "citywalk-enhancing-llmbased-2025",
       "target": "hits-highcoverage-llmbased-2024"
     },
     {
       "source": "citywalk-enhancing-llmbased-2025",
       "target": "codeaware-prompting-study-2024"
     },
     {
       "source": "citywalk-enhancing-llmbased-2025",
       "target": "llm-unit-test-generation-empirical-2024"
     },
     {
       "source": "citywalk-enhancing-llmbased-2025",
       "target": "automated-unit-test-2024"
     },
     {
       "source": "citywalk-enhancing-llmbased-2025",
       "target": "deepseek-v3-2024"
     },
     {
       "source": "citywalk-enhancing-llmbased-2025",
       "target": "llm-hallucinations-code-practical-2024"
     },
     {
       "source": "ckgfuzzer-llmbased-fuzz-2025",
       "target": "llms-se-systematic-review-2023"
     },
     {
       "source": "ckgfuzzer-llmbased-fuzz-2025",
       "target": "llm-fuzzing-challenges-2024"
     },
     {
       "source": "clarifygpt-empowering-llmbased-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "clarifygpt-empowering-llmbased-2023",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "clarifygpt-empowering-llmbased-2023",
       "target": "your-code-generated-2023"
     },
     {
       "source": "clarifygpt-empowering-llmbased-2023",
       "target": "codamosa-escaping-coverage-2023"
     },
     {
       "source": "clarifygpt-empowering-llmbased-2023",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "clarifygpt-empowering-llmbased-2023",
       "target": "interactive-code-generation-2022"
     },
     {
       "source": "clarifygpt-empowering-llmbased-2023",
       "target": "alphacode-competition-level-2022"
     },
     {
       "source": "clarifygpt-framework-enhancing-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "clarifygpt-framework-enhancing-2024",
       "target": "your-code-generated-2023"
     },
     {
       "source": "clarifygpt-framework-enhancing-2024",
       "target": "codamosa-escaping-coverage-2023"
     },
     {
       "source": "clarifygpt-framework-enhancing-2024",
       "target": "interactive-code-generation-2022"
     },
     {
       "source": "clarifygpt-framework-enhancing-2024",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "classeval-manuallycrafted-benchmark-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "classeval-manuallycrafted-benchmark-2023",
       "target": "your-code-generated-2023"
     },
     {
       "source": "classeval-manuallycrafted-benchmark-2023",
       "target": "wizardcoder-empowering-code-2023"
     },
     {
       "source": "classeval-manuallycrafted-benchmark-2023",
       "target": "starcoder-2023"
     },
     {
       "source": "classeval-manuallycrafted-benchmark-2023",
       "target": "lost-middle-how-2023"
     },
     {
       "source": "classeval-manuallycrafted-benchmark-2023",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "classeval-manuallycrafted-benchmark-2023",
       "target": "alphacode-competition-level-2022"
     },
     {
       "source": "classifying-addressing-diversity-2025",
       "target": "ares-automated-evaluation-2023"
     },
     {
       "source": "classifying-addressing-diversity-2025",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "classifying-addressing-diversity-2025",
       "target": "survey-hallucination-large-2023-2"
     },
     {
       "source": "classifying-addressing-diversity-2025",
       "target": "selfconsistency-improves-chain-2022"
     },
     {
       "source": "classit-conversational-lecturealigned-2025",
       "target": "emergent-abilities-large-2022"
     },
     {
       "source": "classit-conversational-lecturealigned-2025",
       "target": "emergent-abilities-mirage-2023"
     },
     {
       "source": "classit-conversational-lecturealigned-2025",
       "target": "llama-3-herd-2024"
     },
     {
       "source": "claude-sonnet-45-2025",
       "target": "alignment-faking-2024"
     },
     {
       "source": "cloud-platforms-developing-2024",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "cloud-platforms-developing-2024",
       "target": "llama-3-herd-2024"
     },
     {
       "source": "cloudevalyaml-practical-benchmark-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "cloudevalyaml-practical-benchmark-2023",
       "target": "code-llama-2023"
     },
     {
       "source": "cloudevalyaml-practical-benchmark-2023",
       "target": "wizardcoder-empowering-code-2023"
     },
     {
       "source": "cloudfix-automated-policy-2025",
       "target": "llms-se-systematic-review-2023"
     },
     {
       "source": "cloudfix-automated-policy-2025",
       "target": "systematic-literature-review-2024"
     },
     {
       "source": "cloudfix-automated-policy-2025",
       "target": "hybrid-automated-program-2024"
     },
     {
       "source": "cloudfix-automated-policy-2025",
       "target": "deep-dive-into-2024-2"
     },
     {
       "source": "cloudfix-automated-policy-2025",
       "target": "automated-program-repair-2022"
     },
     {
       "source": "cloudfix-automated-policy-2025",
       "target": "exploring-generalizable-automated-2025"
     },
     {
       "source": "cloudfix-automated-policy-2025",
       "target": "survey-hallucination-large-2023-2"
     },
     {
       "source": "cmoe-converting-mixtureofexperts-2025",
       "target": "deepseek-v3-2024"
     },
     {
       "source": "cocomic-code-completion-2022",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "cocomic-code-completion-2022",
       "target": "repocoder-repositorylevel-code-2023"
     },
     {
       "source": "cocomic-code-completion-2022",
       "target": "alphacode-competition-level-2022"
     },
     {
       "source": "codamosa-escaping-coverage-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "codamosa-escaping-coverage-2023",
       "target": "productivity-assessment-neural-2022"
     },
     {
       "source": "codamosa-escaping-coverage-2023",
       "target": "alphacode-competition-level-2022"
     },
     {
       "source": "code-aesthetics-agentic-2025",
       "target": "drawing-pandas-benchmark-2024"
     },
     {
       "source": "code-aesthetics-agentic-2025",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "code-hallucination-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "code-hallucination-2024",
       "target": "beyond-functional-correctness-2024"
     },
     {
       "source": "code-hallucination-2024",
       "target": "swe-bench-2023"
     },
     {
       "source": "code-hallucination-2024",
       "target": "your-code-generated-2023"
     },
     {
       "source": "code-hallucination-2024",
       "target": "llms-se-systematic-review-2023"
     },
     {
       "source": "code-hallucination-2024",
       "target": "hallucination-inevitable-innate-2024"
     },
     {
       "source": "code-hallucinations-slr-2025",
       "target": "hallucination-by-code-2025"
     },
     {
       "source": "code-hallucinations-slr-2025",
       "target": "beyond-functional-correctness-2024"
     },
     {
       "source": "code-hallucinations-slr-2025",
       "target": "llm-hallucinations-code-practical-2024"
     },
     {
       "source": "code-hallucinations-slr-2025",
       "target": "codemirage-hallucinations-code-2024"
     },
     {
       "source": "code-hallucinations-slr-2025",
       "target": "survey-hallucination-large-2023-2"
     },
     {
       "source": "code-hallucinations-slr-2025",
       "target": "dehallucinator-mitigating-llm-2024"
     },
     {
       "source": "code-hallucinations-slr-2025",
       "target": "mitigating-api-hallucination-2025"
     },
     {
       "source": "code-hallucinations-slr-2025",
       "target": "gorilla-large-language-2023"
     },
     {
       "source": "code-hallucinations-slr-2025",
       "target": "bugs-large-language-2024"
     },
     {
       "source": "code-hallucinations-slr-2025",
       "target": "identifying-mitigating-api-2025"
     },
     {
       "source": "code-less-align-2024",
       "target": "magicoder-source-code-2023"
     },
     {
       "source": "code-less-align-2024",
       "target": "wizardcoder-empowering-code-2023"
     },
     {
       "source": "code-less-align-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "code-less-align-2024",
       "target": "your-code-generated-2023"
     },
     {
       "source": "code-less-align-2024",
       "target": "code-llama-2023"
     },
     {
       "source": "code-less-align-2024",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "code-llama-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "code-llama-2023",
       "target": "starcoder-2023"
     },
     {
       "source": "code-llama-2023",
       "target": "alphacode-competition-level-2022"
     },
     {
       "source": "code-llama-2023",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "code-llama-2023",
       "target": "multiple-scalable-polyglot-2023"
     },
     {
       "source": "code-me-me-2025",
       "target": "openhands-ai-sw-agent-2024"
     },
     {
       "source": "code-me-me-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "code-me-me-2025",
       "target": "copilot-productivity-controlled-2023"
     },
     {
       "source": "code-me-me-2025",
       "target": "gaia-benchmark-general-2023"
     },
     {
       "source": "code-me-me-2025",
       "target": "metr-rct-2025"
     },
     {
       "source": "code-me-me-2025",
       "target": "rise-ai-teammates-2025"
     },
     {
       "source": "code-me-me-2025",
       "target": "ambigswe-interactive-agents-2025"
     },
     {
       "source": "code-review-automation-2025",
       "target": "codebert-pretrained-model-2020"
     },
     {
       "source": "code-review-survey-pre-post-llm-2026",
       "target": "codereviewqa-code-review-2025"
     },
     {
       "source": "code-review-survey-pre-post-llm-2026",
       "target": "bitsaicr-automated-code-2025"
     },
     {
       "source": "code-review-survey-pre-post-llm-2026",
       "target": "aiassisted-fixes-code-2025"
     },
     {
       "source": "code-review-survey-pre-post-llm-2026",
       "target": "llm-code-review-benchmarking-2025"
     },
     {
       "source": "codearena-collective-evaluation-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "codearena-collective-evaluation-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "codearena-collective-evaluation-2025",
       "target": "bigcodebench-2024"
     },
     {
       "source": "codearena-collective-evaluation-2025",
       "target": "mercury-efficiency-benchmark-2024"
     },
     {
       "source": "codearena-collective-evaluation-2025",
       "target": "deepseek-coder-v2-2024"
     },
     {
       "source": "codearena-collective-evaluation-2025",
       "target": "your-code-generated-2023"
     },
     {
       "source": "codearena-collective-evaluation-2025",
       "target": "starcoder2-2024"
     },
     {
       "source": "codearena-collective-evaluation-2025",
       "target": "code-llama-2023"
     },
     {
       "source": "codeaware-prompting-study-2024",
       "target": "codamosa-escaping-coverage-2023"
     },
     {
       "source": "codeaware-prompting-study-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "codeaware-prompting-study-2024",
       "target": "no-more-manual-2023"
     },
     {
       "source": "codeaware-prompting-study-2024",
       "target": "adaptive-test-generation-2023"
     },
     {
       "source": "codeaware-prompting-study-2024",
       "target": "chatunitest-framework-llmbased-2023"
     },
     {
       "source": "codeaware-prompting-study-2024",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "codeaware-prompting-study-2024",
       "target": "tree-thoughts-deliberate-2023"
     },
     {
       "source": "codebenchgen-creating-scalable-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "codebenchgen-creating-scalable-2024",
       "target": "swe-bench-2023"
     },
     {
       "source": "codebenchgen-creating-scalable-2024",
       "target": "your-code-generated-2023"
     },
     {
       "source": "codebenchgen-creating-scalable-2024",
       "target": "repocoder-repositorylevel-code-2023"
     },
     {
       "source": "codebenchgen-creating-scalable-2024",
       "target": "code-llama-2023"
     },
     {
       "source": "codebert-pretrained-model-2020",
       "target": "bert-pretraining-deep-2018"
     },
     {
       "source": "codecontests-highquality-test-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "codecontests-highquality-test-2025",
       "target": "competitive-programming-reasoning-models-2025"
     },
     {
       "source": "codecontests-highquality-test-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "codecontests-highquality-test-2025",
       "target": "alphacode-competition-level-2022"
     },
     {
       "source": "codecontests-highquality-test-2025",
       "target": "your-code-generated-2023"
     },
     {
       "source": "codecontests-highquality-test-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "codecontests-highquality-test-2025",
       "target": "dapo-opensource-llm-2025"
     },
     {
       "source": "codecontests-highquality-test-2025",
       "target": "qwen25-technical-report-2024"
     },
     {
       "source": "codecor-llmbased-selfreflective-2025",
       "target": "mapcoder-multiagent-code-2024"
     },
     {
       "source": "codecor-llmbased-selfreflective-2025",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "codecor-llmbased-selfreflective-2025",
       "target": "chatdev-communicative-agents-2023"
     },
     {
       "source": "codecor-llmbased-selfreflective-2025",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "codecor-llmbased-selfreflective-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "codecor-llmbased-selfreflective-2025",
       "target": "code-llama-2023"
     },
     {
       "source": "codecriticbench-holistic-code-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "codecriticbench-holistic-code-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "codecriticbench-holistic-code-2025",
       "target": "llm-critics-help-2024"
     },
     {
       "source": "codecriticbench-holistic-code-2025",
       "target": "qwen25coder-technical-report-2024"
     },
     {
       "source": "codecriticbench-holistic-code-2025",
       "target": "deepseek-coder-2024"
     },
     {
       "source": "codediting-reasoningbased-metric-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "codediting-reasoningbased-metric-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "codediting-reasoningbased-metric-2025",
       "target": "your-code-generated-2023"
     },
     {
       "source": "codediting-reasoningbased-metric-2025",
       "target": "bigcodebench-2024"
     },
     {
       "source": "codediting-reasoningbased-metric-2025",
       "target": "codejudge-evaluating-code-2024"
     },
     {
       "source": "codediting-reasoningbased-metric-2025",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "codediting-reasoningbased-metric-2025",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "codediting-reasoningbased-metric-2025",
       "target": "llms-se-systematic-review-2023"
     },
     {
       "source": "codediting-reasoningbased-metric-2025",
       "target": "from-code-courtroom-2025"
     },
     {
       "source": "codeelo-benchmarking-competitionlevel-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "codeelo-benchmarking-competitionlevel-2025",
       "target": "alphacode-competition-level-2022"
     },
     {
       "source": "codeelo-benchmarking-competitionlevel-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "codeelo-benchmarking-competitionlevel-2025",
       "target": "bigcodebench-2024"
     },
     {
       "source": "codeelo-benchmarking-competitionlevel-2025",
       "target": "qwen25coder-technical-report-2024"
     },
     {
       "source": "codeelo-benchmarking-competitionlevel-2025",
       "target": "deepseek-coder-2024"
     },
     {
       "source": "codeelo-benchmarking-competitionlevel-2025",
       "target": "deepseek-coder-v2-2024"
     },
     {
       "source": "codeelo-benchmarking-competitionlevel-2025",
       "target": "llama-3-herd-2024"
     },
     {
       "source": "codegrag-bridging-gap-2024",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "codegrag-bridging-gap-2024",
       "target": "code-llama-2023"
     },
     {
       "source": "codegrag-bridging-gap-2024",
       "target": "reacc-retrievalaugmented-code-2022"
     },
     {
       "source": "codegrag-bridging-gap-2024",
       "target": "evor-evolving-retrieval-2024"
     },
     {
       "source": "codegrag-bridging-gap-2024",
       "target": "codebert-pretrained-model-2020"
     },
     {
       "source": "codeinsight-curated-dataset-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "codeinsight-curated-dataset-2024",
       "target": "code-llama-2023"
     },
     {
       "source": "codeinsight-curated-dataset-2024",
       "target": "starcoder-2023"
     },
     {
       "source": "codejudge-evaluating-code-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "codejudge-evaluating-code-2024",
       "target": "your-code-generated-2023"
     },
     {
       "source": "codejudge-evaluating-code-2024",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "codejudge-evaluating-code-2024",
       "target": "bigcodebench-2024"
     },
     {
       "source": "codejudge-evaluating-code-2024",
       "target": "chateval-better-llmbased-2023"
     },
     {
       "source": "codejudge-evaluating-code-2024",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "codejudgebench-benchmarking-llmasajudge-2025",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "codejudgebench-benchmarking-llmasajudge-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "codejudgebench-benchmarking-llmasajudge-2025",
       "target": "from-code-courtroom-2025"
     },
     {
       "source": "codemark-imperceptible-watermarking-2023",
       "target": "starcoder-2023"
     },
     {
       "source": "codemirage-hallucinations-code-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "codemirage-hallucinations-code-2024",
       "target": "code-llama-2023"
     },
     {
       "source": "codemirage-hallucinations-code-2024",
       "target": "codebert-pretrained-model-2020"
     },
     {
       "source": "codemirage-hallucinations-code-2024",
       "target": "your-code-generated-2023"
     },
     {
       "source": "codemirage-hallucinations-code-2024",
       "target": "large-language-models-2023-3"
     },
     {
       "source": "codemirage-hallucinations-code-2024",
       "target": "sirens-song-ai-2023"
     },
     {
       "source": "codemmlu-multitask-benchmark-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "codemmlu-multitask-benchmark-2024",
       "target": "mmlu-measuring-massive-2020"
     },
     {
       "source": "codemmlu-multitask-benchmark-2024",
       "target": "cruxeval-benchmark-code-2024"
     },
     {
       "source": "codemmlu-multitask-benchmark-2024",
       "target": "livecodebench-2024"
     },
     {
       "source": "codemmlu-multitask-benchmark-2024",
       "target": "leakage-code-generation-2024"
     },
     {
       "source": "codemmlu-multitask-benchmark-2024",
       "target": "your-code-generated-2023"
     },
     {
       "source": "codemmlu-multitask-benchmark-2024",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "codemmlu-multitask-benchmark-2024",
       "target": "starcoder2-2024"
     },
     {
       "source": "codemmlu-multitask-benchmark-2024-2",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "codemmlu-multitask-benchmark-2024-2",
       "target": "mmlu-measuring-massive-2020"
     },
     {
       "source": "codemmlu-multitask-benchmark-2024-2",
       "target": "cruxeval-benchmark-code-2024"
     },
     {
       "source": "codemmlu-multitask-benchmark-2024-2",
       "target": "livecodebench-2024"
     },
     {
       "source": "codemmlu-multitask-benchmark-2024-2",
       "target": "bigcodebench-2024"
     },
     {
       "source": "codemmlu-multitask-benchmark-2024-2",
       "target": "leakage-code-generation-2024"
     },
     {
       "source": "codemmlu-multitask-benchmark-2024-2",
       "target": "your-code-generated-2023"
     },
     {
       "source": "codemmlu-multitask-benchmark-2024-2",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "codemorph-mitigating-data-2025",
       "target": "quantifying-contamination-evaluating-2024"
     },
     {
       "source": "codemorph-mitigating-data-2025",
       "target": "concerned-data-contamination-2024"
     },
     {
       "source": "codemorph-mitigating-data-2025",
       "target": "rethinking-benchmark-contamination-2023"
     },
     {
       "source": "codemorph-mitigating-data-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "codemorph-mitigating-data-2025",
       "target": "top-leaderboard-ranking-2024"
     },
     {
       "source": "codemorph-mitigating-data-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "codemorph-mitigating-data-2025",
       "target": "your-code-generated-2023"
     },
     {
       "source": "codemorph-mitigating-data-2025",
       "target": "benchmark-contamination-survey-2024"
     },
     {
       "source": "codemorph-mitigating-data-2025",
       "target": "bigcodebench-2024"
     },
     {
       "source": "codemorph-mitigating-data-2025",
       "target": "llms-se-systematic-review-2023"
     },
     {
       "source": "codepde-inference-framework-2025",
       "target": "mlebench-evaluating-machine-2024"
     },
     {
       "source": "codepromptzip-codespecific-prompt-2025",
       "target": "code-llama-2023"
     },
     {
       "source": "coderagbench-can-retrieval-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "coderagbench-can-retrieval-2024",
       "target": "swe-bench-2023"
     },
     {
       "source": "coderagbench-can-retrieval-2024",
       "target": "agentless-2024"
     },
     {
       "source": "coderagbench-can-retrieval-2024",
       "target": "livecodebench-2024"
     },
     {
       "source": "coderagbench-can-retrieval-2024",
       "target": "swe-agent-2024"
     },
     {
       "source": "coderagbench-can-retrieval-2024",
       "target": "deepseek-coder-2024"
     },
     {
       "source": "coderagbench-can-retrieval-2024",
       "target": "starcoder-2023"
     },
     {
       "source": "coderagbench-can-retrieval-2024",
       "target": "repocoder-repositorylevel-code-2023"
     },
     {
       "source": "coderagbench-can-retrieval-2024",
       "target": "your-code-generated-2023"
     },
     {
       "source": "coderagbench-can-retrieval-2024",
       "target": "arks-active-retrieval-2024"
     },
     {
       "source": "codereviewqa-code-review-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "codereviewqa-code-review-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "codereviewqa-code-review-2025",
       "target": "bigcodebench-2024"
     },
     {
       "source": "coderl-improving-code-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "coderl-improving-code-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "coderl-improving-code-2025",
       "target": "qwen25coder-technical-report-2024"
     },
     {
       "source": "codescope-executionbased-multilingual-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "codescope-executionbased-multilingual-2023",
       "target": "wizardcoder-empowering-code-2023"
     },
     {
       "source": "codescope-executionbased-multilingual-2023",
       "target": "code-llama-2023"
     },
     {
       "source": "codescope-executionbased-multilingual-2023",
       "target": "starcoder-2023"
     },
     {
       "source": "codescope-executionbased-multilingual-2023",
       "target": "classeval-manuallycrafted-benchmark-2023"
     },
     {
       "source": "codescope-executionbased-multilingual-2023",
       "target": "no-more-manual-2023"
     },
     {
       "source": "codescore-evaluating-code-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "codescore-evaluating-code-2023",
       "target": "starcoder-2023"
     },
     {
       "source": "codescore-evaluating-code-2023",
       "target": "code-llama-2023"
     },
     {
       "source": "codesift-llmbased-referenceless-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "codesift-llmbased-referenceless-2024",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "codesift-llmbased-referenceless-2024",
       "target": "your-code-generated-2023"
     },
     {
       "source": "codesift-llmbased-referenceless-2024",
       "target": "codamosa-escaping-coverage-2023"
     },
     {
       "source": "codesift-llmbased-referenceless-2024",
       "target": "starcoder-2023"
     },
     {
       "source": "codesift-llmbased-referenceless-2024",
       "target": "code-llama-2023"
     },
     {
       "source": "codetm4-detecting-machinegenerated-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "codetm4-detecting-machinegenerated-2025",
       "target": "codebert-pretrained-model-2020"
     },
     {
       "source": "codetm4-detecting-machinegenerated-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "codex-humaneval-2021",
       "target": "scaling-laws-2020"
     },
     {
       "source": "codex-humaneval-2021",
       "target": "codebert-pretrained-model-2020"
     },
     {
       "source": "codexity-secure-aiassisted-2024",
       "target": "copilot-security-weaknesses-2023"
     },
     {
       "source": "codexity-secure-aiassisted-2024",
       "target": "starcoder-2023"
     },
     {
       "source": "codexity-secure-aiassisted-2024",
       "target": "scaffolded-model-capability-2023"
     },
     {
       "source": "codified-context-infrastructure-2026",
       "target": "uc-berkeley-mast-2025"
     },
     {
       "source": "codified-context-infrastructure-2026",
       "target": "context-engineering-ai-2025"
     },
     {
       "source": "codified-context-infrastructure-2026",
       "target": "agentic-ai-software-2025-2"
     },
     {
       "source": "codified-context-infrastructure-2026",
       "target": "agentic-adoption-github-2026"
     },
     {
       "source": "coding-agents-generating-2026",
       "target": "metr-rct-2025"
     },
     {
       "source": "coding-agents-generating-2026",
       "target": "understanding-software-engineering-2025"
     },
     {
       "source": "coding-agents-generating-2026",
       "target": "rise-ai-teammates-2025"
     },
     {
       "source": "coding-agents-generating-2026",
       "target": "agentic-adoption-github-2026"
     },
     {
       "source": "coding-agents-generating-2026",
       "target": "promises-perils-timely-2026"
     },
     {
       "source": "coding-agents-generating-2026",
       "target": "automated-unit-test-2024"
     },
     {
       "source": "coding-agents-generating-2026",
       "target": "test-smells-llmgenerated-2024"
     },
     {
       "source": "coevolving-llm-coder-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "coevolving-llm-coder-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "coevolving-llm-coder-2025",
       "target": "your-code-generated-2023"
     },
     {
       "source": "coevolving-llm-coder-2025",
       "target": "no-more-manual-2023"
     },
     {
       "source": "coevolving-llm-coder-2025",
       "target": "alphacode-competition-level-2022"
     },
     {
       "source": "coffe-code-efficiency-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "coffe-code-efficiency-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "coffe-code-efficiency-2025",
       "target": "evaluating-language-models-2024"
     },
     {
       "source": "coffe-code-efficiency-2025",
       "target": "your-code-generated-2023"
     },
     {
       "source": "coffe-code-efficiency-2025",
       "target": "swe-agent-2024"
     },
     {
       "source": "coffe-code-efficiency-2025",
       "target": "code-llama-2023"
     },
     {
       "source": "coffe-code-efficiency-2025",
       "target": "deepseek-coder-2024"
     },
     {
       "source": "cognitive-control-architecture-2025",
       "target": "agentdojo-dynamic-environment-2024"
     },
     {
       "source": "cognitive-control-architecture-2025",
       "target": "melon-provable-defense-2025"
     },
     {
       "source": "cognitive-control-architecture-2025",
       "target": "not-what-youve-2023"
     },
     {
       "source": "cognitive-control-architecture-2025",
       "target": "ipiguard-novel-tool-2025"
     },
     {
       "source": "cognitive-control-architecture-2025",
       "target": "task-shield-enforcing-2024"
     },
     {
       "source": "cognitive-control-architecture-2025",
       "target": "defending-against-indirect-2024"
     },
     {
       "source": "cognitive-control-architecture-2025",
       "target": "formalizing-benchmarking-prompt-2023"
     },
     {
       "source": "cognitive-control-architecture-2025",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "cognitive-models-ai-2026",
       "target": "tree-thoughts-deliberate-2023"
     },
     {
       "source": "cognitive-models-ai-2026",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "cognitive-models-ai-2026",
       "target": "swe-agent-2024"
     },
     {
       "source": "cognitive-models-ai-2026",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "cognitive-models-ai-2026",
       "target": "openhands-ai-sw-agent-2024"
     },
     {
       "source": "cognitive-models-ai-2026",
       "target": "ai-scientist-fully-2024"
     },
     {
       "source": "cognitive-overload-attackprompt-2024",
       "target": "prompt-injection-llm-apps-2023"
     },
     {
       "source": "cognitive-overload-attackprompt-2024",
       "target": "not-what-youve-2023"
     },
     {
       "source": "coladder-supporting-programmers-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "coladder-supporting-programmers-2023",
       "target": "productivity-assessment-neural-2022"
     },
     {
       "source": "collab-controlled-decoding-2025",
       "target": "transfer-q-star-2024"
     },
     {
       "source": "collaborating-genai-incentives-2025",
       "target": "metr-rct-2025"
     },
     {
       "source": "collaborating-genai-incentives-2025",
       "target": "copilot-productivity-controlled-2023"
     },
     {
       "source": "collaboration-all-you-2025",
       "target": "lost-translation-study-2024"
     },
     {
       "source": "collaboration-all-you-2025",
       "target": "cotran-llmbased-code-2023"
     },
     {
       "source": "collaborative-agents-automated-2025",
       "target": "repairagent-llm-bug-repair-2024"
     },
     {
       "source": "collaborative-agents-automated-2025",
       "target": "openhands-ai-sw-agent-2024"
     },
     {
       "source": "collaborative-agents-automated-2025",
       "target": "demystifying-llmbased-software-2025"
     },
     {
       "source": "collaborative-agents-automated-2025",
       "target": "apr-llm-survey-2025"
     },
     {
       "source": "collaborative-agents-automated-2025",
       "target": "automated-program-repair-2023"
     },
     {
       "source": "collaborative-agents-automated-2025",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "collaborative-agents-automated-2025",
       "target": "systematic-literature-review-2024"
     },
     {
       "source": "collaborative-agents-automated-2025",
       "target": "deepseek-coder-2024"
     },
     {
       "source": "collubench-benchmark-predicting-2024",
       "target": "swe-bench-2023"
     },
     {
       "source": "collubench-benchmark-predicting-2024",
       "target": "swe-agent-2024"
     },
     {
       "source": "collubench-benchmark-predicting-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "collubench-benchmark-predicting-2024",
       "target": "your-code-generated-2023"
     },
     {
       "source": "collubench-benchmark-predicting-2024",
       "target": "impact-code-language-2023"
     },
     {
       "source": "collubench-benchmark-predicting-2024",
       "target": "deep-dive-into-2024-2"
     },
     {
       "source": "collubench-benchmark-predicting-2024",
       "target": "beyond-functional-correctness-2024"
     },
     {
       "source": "collubench-benchmark-predicting-2024",
       "target": "deepseek-coder-2024"
     },
     {
       "source": "collubench-benchmark-predicting-2024",
       "target": "starcoder2-2024"
     },
     {
       "source": "collubench-benchmark-predicting-2024",
       "target": "can-llm-replace-2023"
     },
     {
       "source": "colm-collaborative-large-2025",
       "target": "improving-factuality-reasoning-2023"
     },
     {
       "source": "colm-collaborative-large-2025",
       "target": "think-deep-think-2025"
     },
     {
       "source": "colm-collaborative-large-2025",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "colt-lightweight-multillm-2026",
       "target": "improving-factuality-reasoning-2023"
     },
     {
       "source": "comback-versatile-dataset-2024",
       "target": "code-llama-2023"
     },
     {
       "source": "comback-versatile-dataset-2024",
       "target": "codebert-pretrained-model-2020"
     },
     {
       "source": "combined-approach-program-2024",
       "target": "unified-multitask-learning-2022"
     },
     {
       "source": "combining-costconstrained-runtime-2025",
       "target": "bigcodebench-2024"
     },
     {
       "source": "combining-large-language-2025",
       "target": "repairagent-llm-bug-repair-2024"
     },
     {
       "source": "combining-large-language-2025",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "combining-large-language-2025",
       "target": "no-more-manual-2023"
     },
     {
       "source": "combining-large-language-2025",
       "target": "adaptive-test-generation-2023"
     },
     {
       "source": "comparative-analysis-pretrained-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "comparative-analysis-pretrained-2025",
       "target": "impact-code-language-2023"
     },
     {
       "source": "comparative-analysis-pretrained-2025",
       "target": "how-effective-neural-2023"
     },
     {
       "source": "comparative-analysis-pretrained-2025",
       "target": "less-training-more-2022"
     },
     {
       "source": "comparative-analysis-pretrained-2025",
       "target": "code-llama-2023"
     },
     {
       "source": "comparative-analysis-pretrained-2025",
       "target": "starcoder-2023"
     },
     {
       "source": "comparative-analysis-pretrained-2025",
       "target": "automated-program-repair-2022"
     },
     {
       "source": "comparative-review-ai-2024",
       "target": "alphacode-competition-level-2022"
     },
     {
       "source": "comparative-study-ai-2025",
       "target": "artificial-intelligence-system-2024"
     },
     {
       "source": "comparative-study-dsl-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "comparative-study-dsl-2024",
       "target": "starcoder-2023"
     },
     {
       "source": "comparative-study-dsl-2024",
       "target": "gorilla-large-language-2023"
     },
     {
       "source": "comparative-study-dsl-2024",
       "target": "toolformer-language-models-2023"
     },
     {
       "source": "comparative-study-large-2025",
       "target": "survey-automated-program-2023"
     },
     {
       "source": "comparative-study-large-2025",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "comparative-study-large-2025",
       "target": "survey-learningbased-automated-2023"
     },
     {
       "source": "comparative-study-large-2025",
       "target": "empirical-evaluation-large-2025"
     },
     {
       "source": "comparative-study-large-2025",
       "target": "deepseek-v3-2024"
     },
     {
       "source": "compass-contrastive-learning-2026",
       "target": "codebert-pretrained-model-2020"
     },
     {
       "source": "compass-contrastive-learning-2026",
       "target": "survey-automated-program-2023"
     },
     {
       "source": "compass-contrastive-learning-2026",
       "target": "invalidator-automated-patch-2023"
     },
     {
       "source": "competitive-programming-reasoning-models-2025",
       "target": "alphacode-competition-level-2022"
     },
     {
       "source": "competitive-programming-reasoning-models-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "competitive-programming-reasoning-models-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "competitive-programming-reasoning-models-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "compiler-feedback-loops-2025",
       "target": "llms-se-systematic-review-2023"
     },
     {
       "source": "compiler-feedback-loops-2025",
       "target": "automated-unit-test-2024"
     },
     {
       "source": "compiler-feedback-loops-2025",
       "target": "how-much-does-2024"
     },
     {
       "source": "compiler-feedback-loops-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "compiler-feedback-loops-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "compilernext-searchbased-compiler-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "compilernext-searchbased-compiler-2025",
       "target": "dspy-compiling-declarative-2023"
     },
     {
       "source": "compilernext-searchbased-compiler-2025",
       "target": "autogen-multi-agent-2023"
     },
     {
       "source": "compilernext-searchbased-compiler-2025",
       "target": "adas-automated-design-2024"
     },
     {
       "source": "compilernext-searchbased-compiler-2025",
       "target": "ainative-software-engineering-2024"
     },
     {
       "source": "completion-by-comprehension-2025",
       "target": "deepseek-coder-2024"
     },
     {
       "source": "completion-by-comprehension-2025",
       "target": "code-llama-2023"
     },
     {
       "source": "completion-by-comprehension-2025",
       "target": "crosscodeeval-diverse-multilingual-2023"
     },
     {
       "source": "completion-by-comprehension-2025",
       "target": "repocoder-repositorylevel-code-2023"
     },
     {
       "source": "completion-by-comprehension-2025",
       "target": "rlcoder-reinforcement-learning-2024"
     },
     {
       "source": "completion-by-comprehension-2025",
       "target": "graphcoder-enhancing-repositorylevel-2024"
     },
     {
       "source": "completion-by-comprehension-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "completion-by-comprehension-2025",
       "target": "productivity-assessment-neural-2022"
     },
     {
       "source": "complexcodeeval-benchmark-evaluating-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "complexcodeeval-benchmark-evaluating-2024",
       "target": "deepseek-coder-2024"
     },
     {
       "source": "complexcodeeval-benchmark-evaluating-2024",
       "target": "code-llama-2023"
     },
     {
       "source": "complexcodeeval-benchmark-evaluating-2024",
       "target": "starcoder2-2024"
     },
     {
       "source": "complexcodeeval-benchmark-evaluating-2024",
       "target": "livecodebench-2024"
     },
     {
       "source": "complexcodeeval-benchmark-evaluating-2024",
       "target": "crosscodeeval-diverse-multilingual-2023"
     },
     {
       "source": "complexcodeeval-benchmark-evaluating-2024",
       "target": "classeval-manuallycrafted-benchmark-2023"
     },
     {
       "source": "complexcodeeval-benchmark-evaluating-2024",
       "target": "evocodebench-evolving-code-2024"
     },
     {
       "source": "complexcodeeval-benchmark-evaluating-2024",
       "target": "alphacode-competition-level-2022"
     },
     {
       "source": "compounding-reliability-2025",
       "target": "measuring-ai-ability-2025"
     },
     {
       "source": "compounding-reliability-2025",
       "target": "compute-optimal-inference-2024"
     },
     {
       "source": "compounding-reliability-2025",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "compounding-reliability-2025",
       "target": "bench-benchmark-toolagentuser-2024"
     },
     {
       "source": "compounding-reliability-2025",
       "target": "scaling-laws-2020"
     },
     {
       "source": "compounding-reliability-2025",
       "target": "chinchilla-compute-optimal-2022"
     },
     {
       "source": "comprehensive-analysis-machine-2025",
       "target": "prompt-injection-llm-apps-2023"
     },
     {
       "source": "comprehensive-analysis-machine-2025",
       "target": "not-what-youve-2023"
     },
     {
       "source": "comprehensive-analysis-machine-2025",
       "target": "optimizationbased-prompt-injection-2024"
     },
     {
       "source": "comprehensive-analysis-machine-2025",
       "target": "guardian-multitiered-defense-2024"
     },
     {
       "source": "comprehensive-llm-secure-code-2025",
       "target": "bigcodebench-2024"
     },
     {
       "source": "comprehensive-llm-secure-code-2025",
       "target": "secodeplt-unified-platform-2024"
     },
     {
       "source": "comprehensive-llm-secure-code-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "comprehensive-llm-secure-code-2025",
       "target": "cweval-outcomedriven-evaluation-2025"
     },
     {
       "source": "comprehensive-study-posttraining-2023",
       "target": "smoothquant-accurate-efficient-2022"
     },
     {
       "source": "comprehensive-study-posttraining-2023",
       "target": "case-4bit-precision-2022"
     },
     {
       "source": "comprehensive-survey-aidriven-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "comprehensive-survey-aidriven-2024",
       "target": "deepseek-coder-2024"
     },
     {
       "source": "comprehensive-survey-aidriven-2024",
       "target": "magicoder-source-code-2023"
     },
     {
       "source": "comprehensive-survey-aidriven-2024",
       "target": "starcoder2-2024"
     },
     {
       "source": "comprehensive-survey-llm-2024",
       "target": "constitutional-ai-2022"
     },
     {
       "source": "comprehensive-survey-llm-2024",
       "target": "dpo-superior-ppo-2024"
     },
     {
       "source": "comprehensive-survey-trustworthiness-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "comprehensive-survey-trustworthiness-2025",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "comprehensive-survey-trustworthiness-2025",
       "target": "alignment-faking-2024"
     },
     {
       "source": "comprehensive-taxonomy-hallucinations-2025",
       "target": "codemirage-hallucinations-code-2024"
     },
     {
       "source": "comprehensive-taxonomy-hallucinations-2025",
       "target": "hallulens-llm-hallucination-2025"
     },
     {
       "source": "comprehensive-taxonomy-hallucinations-2025",
       "target": "toolformer-language-models-2023"
     },
     {
       "source": "comprehensive-taxonomy-hallucinations-2025",
       "target": "hallucination-inevitable-innate-2024"
     },
     {
       "source": "comprehensive-taxonomy-hallucinations-2025",
       "target": "sparks-agi-early-2023"
     },
     {
       "source": "comprehensive-verilog-design-2025",
       "target": "verilogeval-evaluating-large-2023"
     },
     {
       "source": "comprehensive-verilog-design-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "comprehensive-verilog-design-2025",
       "target": "copilot-evaluation-harness-2024"
     },
     {
       "source": "compute-optimal-inference-2024",
       "target": "chinchilla-compute-optimal-2022"
     },
     {
       "source": "compute-optimal-inference-2024",
       "target": "beyond-chinchillaoptimal-accounting-2023"
     },
     {
       "source": "compute-optimal-inference-2024",
       "target": "tree-thoughts-deliberate-2023"
     },
     {
       "source": "compute-optimal-inference-2024",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "compute-optimal-inference-2024",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "concept-influence-leveraging-2026",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "conceptguard-neurosymbolic-safety-2025",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "conceptguard-neurosymbolic-safety-2025",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "conceptguard-neurosymbolic-safety-2025",
       "target": "beavertails-improved-safety-2023"
     },
     {
       "source": "concerned-data-contamination-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "concerned-data-contamination-2024",
       "target": "nlp-evaluation-trouble-2023"
     },
     {
       "source": "concerned-data-contamination-2024",
       "target": "classeval-manuallycrafted-benchmark-2023"
     },
     {
       "source": "concerned-data-contamination-2024",
       "target": "how-effective-neural-2023"
     },
     {
       "source": "concrete-roadmap-safety-2025",
       "target": "alignment-faking-2024"
     },
     {
       "source": "concrete-roadmap-safety-2025",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "condor-enhance-llm-2025",
       "target": "self-instruct-aligning-language-2022"
     },
     {
       "source": "condor-enhance-llm-2025",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "condor-enhance-llm-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "confidencedriven-multiscale-model-2026",
       "target": "scaffolded-model-capability-2023"
     },
     {
       "source": "confidencedriven-multiscale-model-2026",
       "target": "scaling-laws-2020"
     },
     {
       "source": "confidenceguided-stepwise-model-2025",
       "target": "beyond-chinchillaoptimal-accounting-2023"
     },
     {
       "source": "confidenceguided-stepwise-model-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "configuring-agentic-coding-tools-2026",
       "target": "cursor-speed-quality-tradeoff-2025"
     },
     {
       "source": "configuring-agentic-coding-tools-2026",
       "target": "context-engineering-ai-2025"
     },
     {
       "source": "configuring-agentic-coding-tools-2026",
       "target": "swe-agent-2024"
     },
     {
       "source": "conformal-constrained-policy-2025",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "conformal-constrained-policy-2025",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "consistency-key-detecting-2025",
       "target": "selfcheckgpt-zeroresource-blackbox-2023"
     },
     {
       "source": "consistency-key-detecting-2025",
       "target": "survey-hallucination-large-2023-2"
     },
     {
       "source": "consistency-key-detecting-2025",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "consistency-key-detecting-2025",
       "target": "hallucination-inevitable-innate-2024"
     },
     {
       "source": "constitutional-ai-2022",
       "target": "beyond-imitation-game-2022"
     },
     {
       "source": "constrained-decoding-diffusion-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "constrained-decoding-diffusion-2025",
       "target": "guiding-llms-right-2024"
     },
     {
       "source": "constrained-decoding-diffusion-2025",
       "target": "syncode-llm-generation-2024"
     },
     {
       "source": "constrained-decoding-diffusion-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "constrained-decoding-diffusion-2025",
       "target": "constrained-decoding-fillinthemiddle-2024"
     },
     {
       "source": "constrained-decoding-diffusion-2025",
       "target": "survey-llm-code-generation-2025"
     },
     {
       "source": "constrained-decoding-fillinthemiddle-2024",
       "target": "starcoder-2023"
     },
     {
       "source": "constrained-decoding-fillinthemiddle-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "constrained-decoding-fillinthemiddle-2024",
       "target": "code-llama-2023"
     },
     {
       "source": "constrained-decoding-fillinthemiddle-2024",
       "target": "efficient-guided-generation-2023"
     },
     {
       "source": "constrained-decoding-fillinthemiddle-2024",
       "target": "syntaxaware-onthefly-code-2022"
     },
     {
       "source": "constrained-decoding-fillinthemiddle-2024",
       "target": "deepseek-coder-v2-2024"
     },
     {
       "source": "context-engineering-ai-2025",
       "target": "llms-se-systematic-review-2023"
     },
     {
       "source": "context-engineering-ai-2025",
       "target": "swe-agent-2024"
     },
     {
       "source": "context-engineering-ai-2025",
       "target": "rise-potential-large-2023"
     },
     {
       "source": "contextaugmented-code-generation-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "contextaugmented-code-generation-2024",
       "target": "coderagbench-can-retrieval-2024"
     },
     {
       "source": "contextaugmented-code-generation-2024",
       "target": "code-llama-2023"
     },
     {
       "source": "contextaugmented-code-generation-2024",
       "target": "deepseek-coder-v2-2024"
     },
     {
       "source": "contextaugmented-code-generation-2024",
       "target": "starcoder2-2024"
     },
     {
       "source": "contextaugmented-code-generation-2024",
       "target": "repocoder-repositorylevel-code-2023"
     },
     {
       "source": "contrastrepair-enhancing-conversationbased-2024",
       "target": "automated-program-repair-2023"
     },
     {
       "source": "contrastrepair-enhancing-conversationbased-2024",
       "target": "less-training-more-2022"
     },
     {
       "source": "contrastrepair-enhancing-conversationbased-2024",
       "target": "impact-code-language-2023"
     },
     {
       "source": "contrastrepair-enhancing-conversationbased-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "contrastrepair-enhancing-conversationbased-2024",
       "target": "your-code-generated-2023"
     },
     {
       "source": "contrastrepair-enhancing-conversationbased-2024",
       "target": "survey-learningbased-automated-2023"
     },
     {
       "source": "control-models-inide-2026",
       "target": "metr-rct-2025"
     },
     {
       "source": "control-models-inide-2026",
       "target": "dont-complete-it-2022"
     },
     {
       "source": "control-models-inide-2026",
       "target": "productivity-assessment-neural-2022"
     },
     {
       "source": "controlled-selfevolution-algorithmic-2026",
       "target": "effilearner-enhancing-efficiency-2024"
     },
     {
       "source": "controlled-selfevolution-algorithmic-2026",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "controlled-selfevolution-algorithmic-2026",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "controlled-selfevolution-algorithmic-2026",
       "target": "survey-code-gen-llm-agents-2025"
     },
     {
       "source": "convergence-dynamics-agenttoagent-2025",
       "target": "prompt-infection-llmtollm-2024"
     },
     {
       "source": "convergence-dynamics-agenttoagent-2025",
       "target": "improving-factuality-reasoning-2023"
     },
     {
       "source": "convergence-dynamics-agenttoagent-2025",
       "target": "rise-potential-large-2023"
     },
     {
       "source": "cooperbench-why-coding-2026",
       "target": "uc-berkeley-mast-2025"
     },
     {
       "source": "cooperbench-why-coding-2026",
       "target": "openhands-ai-sw-agent-2024"
     },
     {
       "source": "cooperbench-why-coding-2026",
       "target": "swe-bench-2023"
     },
     {
       "source": "cooperbench-why-coding-2026",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "cooperbench-why-coding-2026",
       "target": "chatdev-communicative-agents-2023"
     },
     {
       "source": "cooperbench-why-coding-2026",
       "target": "magenticone-generalist-multiagent-2024"
     },
     {
       "source": "cooperbench-why-coding-2026",
       "target": "camel-communicative-agents-2023"
     },
     {
       "source": "copilot-arena-platform-2025",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "copilot-arena-platform-2025",
       "target": "chatbot-arena-open-2024"
     },
     {
       "source": "copilot-arena-platform-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "copilot-arena-platform-2025",
       "target": "bigcodebench-2024"
     },
     {
       "source": "copilot-arena-platform-2025",
       "target": "copilot-productivity-controlled-2023"
     },
     {
       "source": "copilot-arena-platform-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "copilot-arena-platform-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "copilot-arena-platform-2025",
       "target": "livebench-challenging-contaminationlimited-2024"
     },
     {
       "source": "copilot-code-quality-empirical-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "copilot-efficiency-real-world-2024",
       "target": "productivity-assessment-neural-2022"
     },
     {
       "source": "copilot-efficiency-real-world-2024",
       "target": "chatdev-communicative-agents-2023"
     },
     {
       "source": "copilot-evaluation-harness-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "copilot-evaluation-harness-2024",
       "target": "code-llama-2023"
     },
     {
       "source": "copilot-evaluation-harness-2024",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "copilot-evaluation-harness-2024",
       "target": "llms-se-systematic-review-2023"
     },
     {
       "source": "copilot-evaluation-harness-2024",
       "target": "lost-middle-how-2023"
     },
     {
       "source": "copilot-evaluation-harness-2024",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "copilot-longitudinal-case-study-2025",
       "target": "copilot-productivity-controlled-2023"
     },
     {
       "source": "copilot-longitudinal-case-study-2025",
       "target": "generative-ai-at-2023"
     },
     {
       "source": "copilot-productivity-controlled-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "copilot-productivity-controlled-2023",
       "target": "productivity-assessment-neural-2022"
     },
     {
       "source": "copilot-security-weaknesses-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "copilot-security-weaknesses-2023",
       "target": "ai-code-generators-2024"
     },
     {
       "source": "copilot-zoominfo-productivity-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "copilot-zoominfo-productivity-2025",
       "target": "github-copilot-test-2024"
     },
     {
       "source": "copilot-zoominfo-productivity-2025",
       "target": "copilot-code-quality-empirical-2023"
     },
     {
       "source": "copilot-zoominfo-productivity-2025",
       "target": "impact-large-language-2024"
     },
     {
       "source": "copiloting-copilots-fusing-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "copiloting-copilots-fusing-2023",
       "target": "your-code-generated-2023"
     },
     {
       "source": "copiloting-copilots-fusing-2023",
       "target": "alphacode-competition-level-2022"
     },
     {
       "source": "coprompter-usercentric-evaluation-2024",
       "target": "who-validates-validators-2024"
     },
     {
       "source": "core-bench-computational-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "core-bench-computational-2024",
       "target": "swe-bench-2023"
     },
     {
       "source": "core-bench-computational-2024",
       "target": "ai-scientist-fully-2024"
     },
     {
       "source": "core-bench-computational-2024",
       "target": "swe-agent-2024"
     },
     {
       "source": "core-bench-computational-2024",
       "target": "lessons-from-trenches-2024"
     },
     {
       "source": "core-comprehensive-ontological-2026",
       "target": "emergent-abilities-mirage-2023"
     },
     {
       "source": "corecodebench-decoupling-code-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "corecodebench-decoupling-code-2025",
       "target": "swe-bench-2023"
     },
     {
       "source": "corecodebench-decoupling-code-2025",
       "target": "bigcodebench-2024"
     },
     {
       "source": "corecodebench-decoupling-code-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "corecodebench-decoupling-code-2025",
       "target": "your-code-generated-2023"
     },
     {
       "source": "corecodebench-decoupling-code-2025",
       "target": "qwen25coder-technical-report-2024"
     },
     {
       "source": "correctnessguaranteed-code-generation-2025",
       "target": "monitorguided-decoding-code-2023"
     },
     {
       "source": "correctnessguaranteed-code-generation-2025",
       "target": "efficient-guided-generation-2023"
     },
     {
       "source": "cosight-enhancing-llmbased-2025",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "cosight-enhancing-llmbased-2025",
       "target": "gaia-benchmark-general-2023"
     },
     {
       "source": "cosight-enhancing-llmbased-2025",
       "target": "benchmark-expertlevel-academic-2025"
     },
     {
       "source": "cosight-enhancing-llmbased-2025",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "cosight-enhancing-llmbased-2025",
       "target": "improving-factuality-reasoning-2023"
     },
     {
       "source": "cosight-enhancing-llmbased-2025",
       "target": "selfconsistency-improves-chain-2022"
     },
     {
       "source": "cosight-enhancing-llmbased-2025",
       "target": "uc-berkeley-mast-2025"
     },
     {
       "source": "cost-accuracy-longterm-2026",
       "target": "llm-long-term-memory-eval-2024"
     },
     {
       "source": "cost-accuracy-longterm-2026",
       "target": "large-language-model-2024"
     },
     {
       "source": "cost-accuracy-longterm-2026",
       "target": "scaffolded-model-capability-2023"
     },
     {
       "source": "cost-accuracy-longterm-2026",
       "target": "uc-berkeley-mast-2025"
     },
     {
       "source": "cost-dynamic-reasoning-2025",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "cost-dynamic-reasoning-2025",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "cost-dynamic-reasoning-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "cost-dynamic-reasoning-2025",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "cost-dynamic-reasoning-2025",
       "target": "autogen-multi-agent-2023"
     },
     {
       "source": "cotbased-synthesizer-enhancing-2025",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "cotbased-synthesizer-enhancing-2025",
       "target": "selfconsistency-improves-chain-2022"
     },
     {
       "source": "cotbased-synthesizer-enhancing-2025",
       "target": "inference-scaling-laws-2024"
     },
     {
       "source": "cotdeceptoradversarial-code-obfuscation-2025",
       "target": "copilot-security-weaknesses-2023"
     },
     {
       "source": "cotdeceptoradversarial-code-obfuscation-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "cotdeceptoradversarial-code-obfuscation-2025",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "cotrag-integrating-chain-2025",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "cotran-llmbased-code-2023",
       "target": "codebert-pretrained-model-2020"
     },
     {
       "source": "cotran-llmbased-code-2023",
       "target": "rltf-reinforcement-learning-2023"
     },
     {
       "source": "cotran-llmbased-code-2023",
       "target": "compilable-neural-code-2022"
     },
     {
       "source": "courtguard-local-multiagent-2025",
       "target": "adaptive-attacks-break-2025"
     },
     {
       "source": "courtguard-local-multiagent-2025",
       "target": "llmailinject-dataset-from-2025"
     },
     {
       "source": "courtguard-local-multiagent-2025",
       "target": "injecguard-benchmarking-mitigating-2024"
     },
     {
       "source": "courtguard-local-multiagent-2025",
       "target": "backdoored-retrievers-prompt-2024"
     },
     {
       "source": "coverup-effective-high-2024",
       "target": "codamosa-escaping-coverage-2023"
     },
     {
       "source": "coverup-effective-high-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "coverup-effective-high-2024",
       "target": "chatunitest-framework-llmbased-2023"
     },
     {
       "source": "coverup-effective-high-2024",
       "target": "fuzz4all-universal-fuzzing-2023"
     },
     {
       "source": "coverup-effective-high-2024",
       "target": "lost-middle-how-2023"
     },
     {
       "source": "coverup-effective-high-2024",
       "target": "automated-program-repair-2022"
     },
     {
       "source": "cracking-sql-barriers-2025",
       "target": "lost-translation-study-2024"
     },
     {
       "source": "cracking-sql-barriers-2025",
       "target": "starcoder-2023"
     },
     {
       "source": "creativeval-evaluating-creativity-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "creativeval-evaluating-creativity-2024",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "creativeval-evaluating-creativity-2024",
       "target": "verilogeval-evaluating-large-2023"
     },
     {
       "source": "critical-evaluation-defenses-2025",
       "target": "secalign-defending-against-2024"
     },
     {
       "source": "critical-evaluation-defenses-2025",
       "target": "attention-tracker-detecting-2024"
     },
     {
       "source": "critical-evaluation-defenses-2025",
       "target": "formalizing-benchmarking-prompt-2023"
     },
     {
       "source": "critical-evaluation-defenses-2025",
       "target": "automatic-universal-prompt-2024"
     },
     {
       "source": "critical-evaluation-defenses-2025",
       "target": "datasentinel-gametheoretic-detection-2025"
     },
     {
       "source": "critical-review-large-2023",
       "target": "automated-program-repair-2023"
     },
     {
       "source": "critical-review-large-2023",
       "target": "automated-program-repair-2022"
     },
     {
       "source": "critical-review-large-2023",
       "target": "less-training-more-2022"
     },
     {
       "source": "critical-review-large-2023",
       "target": "no-more-manual-2023"
     },
     {
       "source": "crosscodeeval-diverse-multilingual-2023",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "crosscodeeval-diverse-multilingual-2023",
       "target": "starcoder-2023"
     },
     {
       "source": "crosscodeeval-diverse-multilingual-2023",
       "target": "repocoder-repositorylevel-code-2023"
     },
     {
       "source": "crossllm-generalization-behavioral-2025",
       "target": "malice-agentland-down-2025"
     },
     {
       "source": "crossllm-generalization-behavioral-2025",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "crossllm-generalization-behavioral-2025",
       "target": "agentbench-evaluating-llms-2023"
     },
     {
       "source": "crossmodal-memory-compression-2026",
       "target": "improving-factuality-reasoning-2023"
     },
     {
       "source": "crossmodal-memory-compression-2026",
       "target": "uc-berkeley-mast-2025"
     },
     {
       "source": "crossmodal-memory-compression-2026",
       "target": "chateval-better-llmbased-2023"
     },
     {
       "source": "crossmodal-memory-compression-2026",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "crossplatform-evaluation-large-2025",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "crossplatform-evaluation-large-2025",
       "target": "chinchilla-compute-optimal-2022"
     },
     {
       "source": "crqbench-benchmark-code-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "crqbench-benchmark-code-2024",
       "target": "swe-bench-2023"
     },
     {
       "source": "crqbench-benchmark-code-2024",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "crqbench-benchmark-code-2024",
       "target": "can-llm-replace-2023"
     },
     {
       "source": "crqbench-benchmark-code-2024",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "crqbench-benchmark-code-2024",
       "target": "selfconsistency-improves-chain-2022"
     },
     {
       "source": "crscore-reinforcement-learning-2025",
       "target": "combining-large-language-2025"
     },
     {
       "source": "crscore-reinforcement-learning-2025",
       "target": "can-llms-replace-2025"
     },
     {
       "source": "crscore-reinforcement-learning-2025",
       "target": "codereviewqa-code-review-2025"
     },
     {
       "source": "cruxeval-benchmark-code-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "cruxeval-benchmark-code-2024",
       "target": "swe-bench-2023"
     },
     {
       "source": "cruxeval-benchmark-code-2024",
       "target": "code-llama-2023"
     },
     {
       "source": "cruxeval-benchmark-code-2024",
       "target": "your-code-generated-2023"
     },
     {
       "source": "cruxeval-benchmark-code-2024",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "cruxeval-benchmark-code-2024",
       "target": "wizardcoder-empowering-code-2023"
     },
     {
       "source": "cruxevalx-benchmark-multilingual-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "cruxevalx-benchmark-multilingual-2024",
       "target": "cruxeval-benchmark-code-2024"
     },
     {
       "source": "cruxevalx-benchmark-multilingual-2024",
       "target": "multiple-scalable-polyglot-2023"
     },
     {
       "source": "cruxevalx-benchmark-multilingual-2024",
       "target": "swe-bench-2023"
     },
     {
       "source": "cruxevalx-benchmark-multilingual-2024",
       "target": "concerned-data-contamination-2024"
     },
     {
       "source": "cruxevalx-benchmark-multilingual-2024",
       "target": "deepseek-coder-2024"
     },
     {
       "source": "cruxevalx-benchmark-multilingual-2024",
       "target": "your-code-generated-2023"
     },
     {
       "source": "cruxevalx-benchmark-multilingual-2024",
       "target": "code-llama-2023"
     },
     {
       "source": "cuckoo-attack-stealthy-2025",
       "target": "mcp-safety-audit-2025"
     },
     {
       "source": "cuckoo-attack-stealthy-2025",
       "target": "redcode-risky-code-2024"
     },
     {
       "source": "cuckoo-attack-stealthy-2025",
       "target": "prompt-injection-llm-apps-2023"
     },
     {
       "source": "cudaforge-agent-framework-2025",
       "target": "survey-code-gen-llm-agents-2025"
     },
     {
       "source": "cudaforge-agent-framework-2025",
       "target": "survey-llm-code-generation-2025"
     },
     {
       "source": "current-challenges-software-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "current-challenges-software-2024",
       "target": "chatunitest-framework-llmbased-2023"
     },
     {
       "source": "current-challenges-software-2024",
       "target": "deepseek-coder-2024"
     },
     {
       "source": "current-challenges-software-2024",
       "target": "fuzz4all-universal-fuzzing-2023"
     },
     {
       "source": "current-challenges-software-2024",
       "target": "semcoder-training-code-2024"
     },
     {
       "source": "curriculum-guided-massive-2025",
       "target": "emergent-abilities-mirage-2023"
     },
     {
       "source": "curriculum-guided-massive-2025",
       "target": "optima-optimizing-effectiveness-2024"
     },
     {
       "source": "curriculum-guided-massive-2025",
       "target": "plan-and-act-long-horizon-2025"
     },
     {
       "source": "curriculum-guided-massive-2025",
       "target": "selfconsistency-improves-chain-2022"
     },
     {
       "source": "cweval-outcomedriven-evaluation-2025",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "cweval-outcomedriven-evaluation-2025",
       "target": "your-code-generated-2023"
     },
     {
       "source": "cweval-outcomedriven-evaluation-2025",
       "target": "livecodebench-2024"
     },
     {
       "source": "dacode-agent-data-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "dacode-agent-data-2024",
       "target": "swe-bench-2023"
     },
     {
       "source": "dacode-agent-data-2024",
       "target": "autogen-multi-agent-2023"
     },
     {
       "source": "dacode-agent-data-2024",
       "target": "executable-code-actions-2024"
     },
     {
       "source": "dacode-agent-data-2024",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "dancing-critiques-enhancing-2025",
       "target": "selfconsistency-improves-chain-2022"
     },
     {
       "source": "dancing-critiques-enhancing-2025",
       "target": "tree-thoughts-deliberate-2023"
     },
     {
       "source": "dancing-critiques-enhancing-2025",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "dancing-critiques-enhancing-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "dancing-critiques-enhancing-2025",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "dangers-poisoned-llms-2025",
       "target": "sleeper-agents-2024"
     },
     {
       "source": "dangers-poisoned-llms-2025",
       "target": "poisoning-attacks-llms-2025"
     },
     {
       "source": "dapo-opensource-llm-2025",
       "target": "deepseek-r1-2025"
     },
     {
       "source": "dapo-opensource-llm-2025",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "leakage-reproducibility-crisis-2023",
       "target": "neurips-reproducibility-2021"
     },
     {
       "source": "lost-middle-how-2023",
       "target": "toolformer-language-models-2023"
     },
     {
       "source": "lost-middle-how-2023",
       "target": "llama-open-efficient-2023"
     },
     {
       "source": "lost-mix-evaluating-2025",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "lost-mix-evaluating-2025",
       "target": "llama-3-herd-2024"
     },
     {
       "source": "lost-mix-evaluating-2025",
       "target": "mmlu-measuring-massive-2020"
     },
     {
       "source": "lost-mix-evaluating-2025",
       "target": "linguistics-theory-meets-2024"
     },
     {
       "source": "lpcd-unified-framework-2025",
       "target": "llama-3-herd-2024"
     },
     {
       "source": "lutllm-efficient-large-2025",
       "target": "smoothquant-accurate-efficient-2022"
     },
     {
       "source": "lynx-open-source-2024",
       "target": "ragtruth-hallucination-corpus-2023"
     },
     {
       "source": "lynx-open-source-2024",
       "target": "ares-automated-evaluation-2023"
     },
     {
       "source": "lynx-open-source-2024",
       "target": "judging-llmasajudge-mtbench-2023"
     },
     {
       "source": "lynx-open-source-2024",
       "target": "selfcheckgpt-zeroresource-blackbox-2023"
     },
     {
       "source": "lynx-open-source-2024",
       "target": "chain-of-thought-prompting-2022"
     },
     {
       "source": "mactg-multiagent-collaborative-2024",
       "target": "metagpt-multi-agent-framework-2023"
     },
     {
       "source": "mactg-multiagent-collaborative-2024",
       "target": "chatdev-communicative-agents-2023"
     },
     {
       "source": "mactg-multiagent-collaborative-2024",
       "target": "tree-thoughts-deliberate-2023"
     },
     {
       "source": "mactg-multiagent-collaborative-2024",
       "target": "react-synergizing-reasoning-2022"
     },
     {
       "source": "mactg-multiagent-collaborative-2024",
       "target": "survey-autonomous-llm-agents-2023"
     },
     {
       "source": "mactg-multiagent-collaborative-2024",
       "target": "survey-llm-code-generation-2025"
     },
     {
       "source": "mactg-multiagent-collaborative-2024",
       "target": "deepseek-v3-2024"
     },
     {
       "source": "madspear-conformitydriven-prompt-2025",
       "target": "formalizing-benchmarking-prompt-2023"
     },
     {
       "source": "madspear-conformitydriven-prompt-2025",
       "target": "automatic-universal-prompt-2024"
     },
     {
       "source": "madspear-conformitydriven-prompt-2025",
       "target": "improving-factuality-reasoning-2023"
     },
     {
       "source": "madspear-conformitydriven-prompt-2025",
       "target": "which-agent-causes-2025"
     },
     {
       "source": "madspear-conformitydriven-prompt-2025",
       "target": "prompt-infection-llmtollm-2024"
     },
     {
       "source": "maestro-multiagent-evaluation-2026",
       "target": "agentbench-evaluating-llms-2023"
     },
     {
       "source": "maestro-multiagent-evaluation-2026",
       "target": "uc-berkeley-mast-2025"
     },
     {
       "source": "maestro-multiagent-evaluation-2026",
       "target": "magenticone-generalist-multiagent-2024"
     },
     {
       "source": "maestro-multiagent-evaluation-2026",
       "target": "measuring-agents-production-2025"
     },
     {
       "source": "maestro-multiagent-evaluation-2026",
       "target": "reflexion-language-agents-2023"
     },
     {
       "source": "maestro-multiagent-evaluation-2026",
       "target": "tree-thoughts-deliberate-2023"
     },
     {
       "source": "maestro-multiagent-evaluation-2026",
       "target": "lost-middle-how-2023"
     },
     {
       "source": "maestro-multiagent-evaluation-2026",
       "target": "large-language-model-2024"
     },
     {
       "source": "magentic-marketplace-opensource-2025",
       "target": "multiagent-risks-from-2025"
     },
     {
       "source": "magentic-marketplace-opensource-2025",
       "target": "generative-agents-interactive-2023"
     },
     {
       "source": "magentic-marketplace-opensource-2025",
       "target": "from-llm-reasoning-2025"
     },
     {
       "source": "magenticone-generalist-multiagent-2024",
       "target": "autogen-enabling-nextgen-2023"
     },
     {
       "source": "magenticone-generalist-multiagent-2024",
       "target": "gaia-benchmark-general-2023"
     },
     {
       "source": "magenticone-generalist-multiagent-2024",
       "target": "webarena-autonomous-agents-2023"
     },
     {
       "source": "magenticone-generalist-multiagent-2024",
       "target": "swe-bench-2023"
     },
     {
       "source": "magenticone-generalist-multiagent-2024",
       "target": "swe-agent-2024"
     },
     {
       "source": "magenticone-generalist-multiagent-2024",
       "target": "agentless-2024"
     },
     {
       "source": "magenticone-generalist-multiagent-2024",
       "target": "ai-scientist-fully-2024"
     },
     {
       "source": "neurips-reproducibility-2021",
       "target": "deep-rl-matters-2018"
     },
     {
       "source": "neurips-reproducibility-2021",
       "target": "gans-created-equal-2018"
     },
     {
       "source": "neurips-reproducibility-2021",
       "target": "bert-pretraining-deep-2018"
     },
     {
       "source": "questionable-practices-ml-2024",
       "target": "lessons-from-trenches-2024"
     },
     {
       "source": "questionable-practices-ml-2024",
       "target": "troubling-trends-ml-2018"
     },
     {
       "source": "questionable-practices-ml-2024",
       "target": "chatbot-arena-open-2024"
     },
     {
       "source": "questionable-practices-ml-2024",
       "target": "gpt4-technical-report-2023"
     },
     {
       "source": "questionable-practices-ml-2024",
       "target": "codex-humaneval-2021"
     },
     {
       "source": "reproducibility-ml-overview-2025",
       "target": "lessons-from-trenches-2024"
     },
     {
       "source": "reproducibility-ml-overview-2025",
       "target": "leakage-reproducibility-crisis-2023"
     },
     {
       "source": "reproducibility-ml-overview-2025",
       "target": "neurips-reproducibility-2021"
     },
     {
       "source": "show-your-work-2019",
       "target": "troubling-trends-ml-2018"
     },
     {
       "source": "show-your-work-2019",
       "target": "deep-rl-matters-2018"
     },
     {
       "source": "show-your-work-2019",
       "target": "gans-created-equal-2018"
     },
     {
       "source": "troubling-trends-ml-2018",
       "target": "deep-rl-matters-2018"
     },
     {
       "source": "troubling-trends-ml-2018",
       "target": "gans-created-equal-2018"
     },
     {
       "source": "trust-ai-benchmarks-2025",
       "target": "lessons-from-trenches-2024"
     },
     {
       "source": "trust-ai-benchmarks-2025",
       "target": "alignment-faking-2024"
     },
     {
       "source": "trust-ai-benchmarks-2025",
       "target": "not-what-youve-2023"
     },
     {
       "source": "trust-ai-benchmarks-2025",
       "target": "chatbot-arena-open-2024"
     }
   ],
   "most_cited": [
     {
       "slug": "codex-humaneval-2021",
       "incoming_citations": 159
     },
     {
       "slug": "swe-bench-2023",
       "incoming_citations": 63
     },
     {
       "slug": "your-code-generated-2023",
       "incoming_citations": 47
     },
     {
       "slug": "chain-of-thought-prompting-2022",
       "incoming_citations": 46
     },
     {
       "slug": "gpt4-technical-report-2023",
       "incoming_citations": 38
     },
     {
       "slug": "react-synergizing-reasoning-2022",
       "incoming_citations": 38
     },
     {
       "slug": "livecodebench-2024",
       "incoming_citations": 38
     },
     {
       "slug": "judging-llmasajudge-mtbench-2023",
       "incoming_citations": 37
     },
     {
       "slug": "code-llama-2023",
       "incoming_citations": 36
     },
     {
       "slug": "reflexion-language-agents-2023",
       "incoming_citations": 36
     },
     {
       "slug": "deepseek-r1-2025",
       "incoming_citations": 30
     },
     {
       "slug": "metagpt-multi-agent-framework-2023",
       "incoming_citations": 29
     },
     {
       "slug": "sleeper-agents-2024",
       "incoming_citations": 29
     },
     {
       "slug": "not-what-youve-2023",
       "incoming_citations": 27
     },
     {
       "slug": "swe-agent-2024",
       "incoming_citations": 27
     },
     {
       "slug": "autogen-multi-agent-2023",
       "incoming_citations": 23
     },
     {
       "slug": "alphacode-competition-level-2022",
       "incoming_citations": 21
     },
     {
       "slug": "chatdev-communicative-agents-2023",
       "incoming_citations": 20
     },
     {
       "slug": "bigcodebench-2024",
       "incoming_citations": 20
     },
     {
       "slug": "selfconsistency-improves-chain-2022",
       "incoming_citations": 19
     },
     {
       "slug": "starcoder-2023",
       "incoming_citations": 19
     },
     {
       "slug": "tree-thoughts-deliberate-2023",
       "incoming_citations": 18
     },
     {
       "slug": "uc-berkeley-mast-2025",
       "incoming_citations": 18
     },
     {
       "slug": "copilot-productivity-controlled-2023",
       "incoming_citations": 17
     },
     {
       "slug": "llms-se-systematic-review-2023",
       "incoming_citations": 17
     },
     {
       "slug": "codebert-pretrained-model-2020",
       "incoming_citations": 17
     },
     {
       "slug": "deepseek-coder-2024",
       "incoming_citations": 16
     },
     {
       "slug": "emergent-abilities-mirage-2023",
       "incoming_citations": 16
     },
     {
       "slug": "openhands-ai-sw-agent-2024",
       "incoming_citations": 16
     },
     {
       "slug": "formalizing-benchmarking-prompt-2023",
       "incoming_citations": 16
     }
   ],
   "connected_components": {
     "count": 12,
     "largest_size": 752,
     "components": [
       [
         "3dshape2vecset-3d-shape-2023",
         "a2hcoder-llmdriven-coding-2025",
         "aart-aiassisted-redteaming-2023",
         "acar-adaptive-complexity-2026",
         "accelerating-automatic-program-2025",
         "accelerating-large-language-2023",
         "across-programming-language-2025",
         "adafuse-adaptive-ensemble-2026",
         "adaplanner-adaptive-planning-2023",
         "adaptevolve-improving-efficiency-2026",
         "adapting-knowledge-prompt-2025",
         "adaptive-attacks-break-2025",
         "adaptive-attacks-bypass-defenses-2025",
         "adaptive-test-generation-2023",
         "adaptrack-constrained-decoding-2025",
         "adas-automated-design-2024",
         "adoption-generative-artificial-2026",
         "advancements-generative-ai-2023",
         "advancing-code-generation-2025",
         "advancing-language-model-2025",
         "advancing-largemolecule-discovery-2025",
         "advancing-methodological-development-2025",
         "advancing-nursing-regulation-2025",
         "advancing-software-quality-2025",
         "adversarial-bug-reports-2025",
         "adversarial-threat-vectors-2025",
         "advevomarl-shaping-internalized-2025",
         "aegis-automated-coevolutionary-2025",
         "aegis20-diverse-ai-2025",
         "aegisagent-autonomous-defense-2025",
         "agent-contracts-formal-2026",
         "agent-developer-practices-2025",
         "agent-error-taxonomy-2025",
         "agent-security-bench-2024",
         "agentasajudge-evaluate-agents-2024",
         "agentask-multiagent-systems-2025",
         "agentbased-evaluation-framework-2025",
         "agentbench-evaluating-llms-2023",
         "agentdojo-dynamic-environment-2024",
         "agentfuzzer-generic-blackbox-2025",
         "agentic-adoption-github-2026",
         "agentic-ai-architectures-2026",
         "agentic-ai-assessment-framework-2025",
         "agentic-ai-modernization-2026",
         "agentic-ai-security-survey-2025",
         "agentic-ai-software-2025",
         "agentic-ai-software-2025-2",
         "agentic-bug-reproduction-2025",
         "agentic-programming-survey-2025",
         "agentic-refactoring-empirical-2025",
         "agentic-software-engineering-2025",
         "agentless-2024",
         "agentmesh-cooperative-multiagent-2025",
         "agents-of-chaos-2026",
         "agents4plc-automating-closedloop-2024",
         "agentsllm-augmentative-generation-2025",
         "agentsnet-coordination-collaborative-2025",
         "agentspawn-adaptive-multiagent-2026",
         "agenttypo-adaptive-typographic-2025",
         "agentvigil-generic-blackbox-2025",
         "agint-agentic-graph-2025",
         "ai-alignment-contemporary-2025",
         "ai-alignment-strategies-2025",
         "ai-as-cognitive-2025",
         "ai-assistance-legal-2023",
         "ai-code-generators-2024",
         "ai-code-maintainability-registered-report-2024",
         "ai-code-not-reproducible-2025",
         "ai-code-review-2025",
         "ai-code-survival-open-source-2026",
         "ai-code-wild-2025",
         "ai-ides-vs-agents-impact-2026",
         "ai-productivity-index-2025",
         "ai-prs-code-quality-reuse-2026",
         "ai-safety-subproblems-2023",
         "ai-scientist-fully-2024",
         "ai-scientistv2-workshoplevel-2025",
         "ai-software-engineering-2025",
         "ai-testing-should-2025",
         "aiassisted-assessment-coding-2024",
         "aiassisted-code-editors-2025",
         "aiassisted-fixes-code-2025",
         "aiassisted-programming-decreases-2025",
         "aidriven-scholarly-peer-2025",
         "aidriven-software-engineering-2024",
         "aime-ai-system-2024",
         "ainative-software-engineering-2024",
         "ainstein-assessing-feasibility-2025",
         "aipowered-code-review-2023",
         "aipowered-code-review-2024",
         "ais-environmental-cost-2025",
         "aixamine-simplified-llm-2025",
         "aligned-query-expansion-2025",
         "aligning-objective-llmbased-2024",
         "alignment-faking-2024",
         "alignment-safety-llm-survey-2025",
         "alleviating-fear-losing-2025",
         "alphacode-competition-level-2022",
         "ambigswe-interactive-agents-2025",
         "among-us-measuring-2026",
         "among-us-sandbox-2025",
         "analysis-evaluation-synthetic-2025",
         "analysis-studentllm-interaction-2025",
         "anatomy-capability-emergence-2026",
         "ancoder-anchored-code-2026",
         "animagents-coordinating-multistage-2025",
         "annotation-alignment-comparing-2024",
         "antiregulatory-ai-how-2025",
         "appatch-automated-adaptive-2024",
         "applying-rlaif-code-2024",
         "appworld-controllable-world-2024",
         "apr-llm-survey-2025",
         "april-api-synthesis-2025",
         "aptserve-adaptive-request-2025",
         "aquallm-evaluating-accuracy-2025",
         "arcmemo-abstract-reasoning-2025",
         "arcs-agentic-retrievalaugmented-2025",
         "arena-hard-auto-2024",
         "ares-automated-evaluation-2023",
         "argus-defending-against-2025",
         "arks-active-retrieval-2024",
         "art-adaptive-response-2025",
         "art-repair-optimizing-2025",
         "art-scaling-test-time-compute-2025",
         "artifactsbench-bridging-visualinteractive-2025",
         "artificial-brain-neuroscience-2026",
         "artificial-human-intelligence-2025",
         "artificial-intelligence-assistance-2026",
         "artificial-just-artful-2025",
         "artificial-organisations-2026",
         "ask-me-anything-2022",
         "askeda-design-assistant-2024",
         "assessing-answerability-queries-2024",
         "assessing-correctness-llmbased-2025",
         "assessing-domainlevel-susceptibility-2026",
         "assessing-impact-code-2025",
         "assessing-latent-automated-2024",
         "assessing-verifying-task-2024",
         "astrovisbench-code-benchmark-2025",
         "asymptotic-study-incontext-2025",
         "atlas-artifact-generation-2025",
         "atom-thoughts-markov-2025",
         "attacking-llms-ai-2025",
         "attacks-by-content-2025",
         "attention-all-you-2025",
         "attention-is-all-you-need-2017",
         "attention-pruning-automated-2025",
         "attention-tracker-detecting-2024",
         "audit-trails-accountability-2026",
         "auditing-fairness-under-2026",
         "augmented-language-models-2023",
         "autocodebench-large-language-2025",
         "autocypher-improving-llms-2024",
         "autoflow-automated-workflow-2024",
         "autogen-enabling-nextgen-2023",
         "autogen-multi-agent-2023",
         "autokaggle-multiagent-framework-2024",
         "automated-bug-detection-2025",
         "automated-cc-program-2024",
         "automated-code-generation-2025",
         "automated-code-review-practice-2024",
         "automated-discovery-test-2025",
         "automated-extraction-mechanical-2026",
         "automated-formalization-conceptual-2025",
         "automated-knowledge-component-2025",
         "automated-program-repair-2022",
         "automated-program-repair-2023",
         "automated-program-repair-2023-2",
         "automated-program-repair-2024",
         "automated-program-repair-2025",
         "automated-repair-c-2025",
         "automated-smart-contract-2025",
         "automated-structural-testing-2026",
         "automated-test-case-2024",
         "automated-test-generation-2024",
         "automated-unit-test-2024",
         "automatic-generation-benchmarks-2024",
         "automatic-universal-prompt-2024",
         "automatically-benchmarking-code-agents-2025",
         "automatically-generating-web-2025",
         "automatically-surfacing-opportunities-2025",
         "automating-deception-scalable-2025",
         "automating-rest-api-2024",
         "automating-structural-engineering-2025",
         "automation-ai-intergenerational-2025",
         "autonomous-normative-multiagent-2025",
         "autonomous-supplier-evaluation-2025",
         "autop2c-llmbased-agent-2025",
         "autostreampipe-llm-assisted-2025",
         "autotom-scaling-modelbased-2025",
         "autovcoder-systematic-framework-2024",
         "autoverus-automated-proof-2024",
         "awcp-workspace-delegation-2026",
         "backdoor-attribution-elucidating-2025",
         "backdoor-samples-detection-2025",
         "backdoored-retrievers-prompt-2024",
         "backdooring-bias-large-2026",
         "backdoorpowered-prompt-injection-2025",
         "backportbench-multilingual-benchmark-2025",
         "bamas-structuring-budgetaware-2025",
         "bamboo-comprehensive-benchmark-2023",
         "banglaforge-llm-collaboration-2025",
         "bashexplainer-retrievalaugmented-bash-2022",
         "battleagentbench-benchmark-evaluating-2024",
         "bayesian-reward-models-2024",
         "beavertails-improved-safety-2023",
         "behavior-alignment-new-2024",
         "bench-benchmark-toolagentuser-2024",
         "benchmark-contamination-survey-2024",
         "benchmark-expertlevel-academic-2025",
         "benchmark-test-time-scaling-agents-2026",
         "benchmarking-ai-models-2025",
         "benchmarking-ai-models-2025-2",
         "benchmarking-epistemology-construct-2025",
         "benchmarking-hallucination-large-2024",
         "benchmarking-large-language-2022",
         "benchmarking-large-language-2024",
         "benchmarking-llms-unit-2025",
         "benchmarks-automated-commonsense-2023",
         "bert-pretraining-deep-2018",
         "best-practices-ai-2023",
         "beyond-automation-job-redesign-2025",
         "beyond-benchmark-innovative-2025",
         "beyond-chinchillaoptimal-accounting-2023",
         "beyond-chunks-graphs-2025",
         "beyond-commit-developer-perspectives-2026",
         "beyond-correctness-benchmarking-2024",
         "beyond-correctness-rewarding-2025",
         "beyond-functional-correctness-2024",
         "beyond-imitation-game-2022",
         "beyond-mimicry-preference-2025",
         "beyond-promptinduced-lies-2025",
         "beyond-quantity-trajectory-2026",
         "beyond-singleagent-safety-2025",
         "beyond-static-datasets-2023",
         "beyond-static-pattern-2025",
         "beyond-synthetic-benchmarks-2025",
         "beyond-textual-context-2025",
         "beyond-token-probes-2025",
         "bias-assessment-mitigation-2023",
         "bias-unveiled-investigating-2024",
         "biasalert-plugandplay-tool-2024",
         "bigcodebench-2024",
         "bigrpo-bidirectional-optimization-2025",
         "bioplanner-automatic-evaluation-2023",
         "biotrouble-multiagent-workflow-2026",
         "bitsaicr-automated-code-2025",
         "blockdialect-blockwise-finegrained-2025",
         "boosting-llm-reasoning-2025",
         "boosting-redundancybased-automated-2023",
         "bottomup-domainspecific-superintelligence-2025",
         "bpo-staying-close-2024",
         "break-sequential-dependency-2024",
         "breaking-prompt-wall-2025",
         "bridging-human-interpretation-2026",
         "bridging-llmgenerated-code-2025",
         "broken-neural-scaling-2022",
         "browserarena-web-agents-2025",
         "browsesafe-understanding-preventing-2025",
         "budgetaware-agentic-routing-2026",
         "bugdar-aiaugmented-secure-2025",
         "bugs-large-language-2024",
         "build-your-personalized-2025",
         "building-coding-assistant-2024",
         "building-cooperative-embodied-2023",
         "building-early-warning-2024",
         "building-understandable-messaging-2024",
         "bypassing-llm-guardrails-2025",
         "bytesized32refactored-extensible-interactive-2025",
         "c3po-optimized-large-2025",
         "cacheprune-neuralbased-attribution-2025",
         "calibrating-llm-judges-2025",
         "calibration-large-language-2026",
         "camel-communicative-agents-2023",
         "can-1b-llm-2025",
         "can-chatgpt-support-2024",
         "can-indirect-prompt-2025",
         "can-large-language-2025",
         "can-llm-replace-2023",
         "can-llms-replace-2025",
         "can-reasoning-models-2025",
         "can-vibe-coding-2025",
         "canaries-coal-mine-2025",
         "capability-ceilings-autoregressive-2025",
         "capabilityoriented-training-induced-2026",
         "capture-contextaware-prompt-2025",
         "carbon-footprint-evaluation-2025",
         "case-4bit-precision-2022",
         "case-study-transformative-2025",
         "cast-enhancing-code-2025",
         "caster-breaking-costperformance-2026",
         "catarena-evaluating-evolutionary-2025",
         "catch-me-if-2025",
         "catdb-datacatalogguided-llmbased-2025",
         "causalarmor-efficient-indirect-2026",
         "cbfllm-safe-control-2024",
         "cctest-testing-repairing-2022",
         "chain-of-thought-prompting-2022",
         "chainofthought-prompting-obscures-2025",
         "chainpoll-high-efficacy-2023",
         "challenge-optimization-context-2025",
         "challenges-humanagent-communication-2024",
         "challenges-paths-ai-2025",
         "changes-coding-behavior-2026",
         "characterizing-llm-inference-2025",
         "chasing-progress-not-2024",
         "chat-bankmanfried-exploration-2024",
         "chatassert-llmbased-test-2025",
         "chatbot-arena-open-2024",
         "chatdev-communicative-agents-2023",
         "chateval-better-llmbased-2023",
         "chatgpt-agent-system-2025",
         "chatgpt-not-all-2023",
         "chatinject-abusing-chat-2025",
         "chatofthought-collaborative-multiagent-2025",
         "chatunitest-framework-llmbased-2023",
         "check-your-facts-2023",
         "checkpointgcg-auditing-attacking-2025",
         "chinchilla-compute-optimal-2022",
         "chipbench-nextstep-benchmark-2026",
         "chopchop-programmable-framework-2025",
         "chorus-zeroshot-hierarchical-2025",
         "ciata-risk-assessment-2025",
         "cigar-costefficient-program-2024",
         "citationenhanced-generation-llmbased-2024",
         "citationgrounded-code-comprehension-2025",
         "citywalk-enhancing-llmbased-2025",
         "ckgfuzzer-llmbased-fuzz-2025",
         "clarifygpt-empowering-llmbased-2023",
         "clarifygpt-framework-enhancing-2024",
         "classeval-manuallycrafted-benchmark-2023",
         "classifying-addressing-diversity-2025",
         "classit-conversational-lecturealigned-2025",
         "claude-sonnet-45-2025",
         "cloud-platforms-developing-2024",
         "cloudevalyaml-practical-benchmark-2023",
         "cloudfix-automated-policy-2025",
         "cmoe-converting-mixtureofexperts-2025",
         "cocomic-code-completion-2022",
         "codamosa-escaping-coverage-2023",
         "code-aesthetics-agentic-2025",
         "code-hallucination-2024",
         "code-hallucinations-slr-2025",
         "code-less-align-2024",
         "code-llama-2023",
         "code-me-me-2025",
         "code-review-automation-2025",
         "code-review-survey-pre-post-llm-2026",
         "codearena-collective-evaluation-2025",
         "codeaware-prompting-study-2024",
         "codebenchgen-creating-scalable-2024",
         "codebert-pretrained-model-2020",
         "codecontests-highquality-test-2025",
         "codecor-llmbased-selfreflective-2025",
         "codecriticbench-holistic-code-2025",
         "codediting-reasoningbased-metric-2025",
         "codeelo-benchmarking-competitionlevel-2025",
         "codefill-multitoken-code-2022",
         "codegrag-bridging-gap-2024",
         "codeinsight-curated-dataset-2024",
         "codejudge-evaluating-code-2024",
         "codejudgebench-benchmarking-llmasajudge-2025",
         "codemark-imperceptible-watermarking-2023",
         "codemirage-hallucinations-code-2024",
         "codemmlu-multitask-benchmark-2024",
         "codemmlu-multitask-benchmark-2024-2",
         "codemorph-mitigating-data-2025",
         "codepde-inference-framework-2025",
         "codepromptzip-codespecific-prompt-2025",
         "coderagbench-can-retrieval-2024",
         "codereviewqa-code-review-2025",
         "coderl-improving-code-2025",
         "codescope-executionbased-multilingual-2023",
         "codescore-evaluating-code-2023",
         "codesift-llmbased-referenceless-2024",
         "codetm4-detecting-machinegenerated-2025",
         "codex-humaneval-2021",
         "codexity-secure-aiassisted-2024",
         "codified-context-infrastructure-2026",
         "coding-agents-generating-2026",
         "coevolving-llm-coder-2025",
         "coffe-code-efficiency-2025",
         "cognitive-control-architecture-2025",
         "cognitive-models-ai-2026",
         "cognitive-overload-attackprompt-2024",
         "coladder-supporting-programmers-2023",
         "collaborating-genai-incentives-2025",
         "collaboration-all-you-2025",
         "collaborative-agents-automated-2025",
         "collubench-benchmark-predicting-2024",
         "colm-collaborative-large-2025",
         "colt-lightweight-multillm-2026",
         "comback-versatile-dataset-2024",
         "combining-costconstrained-runtime-2025",
         "combining-large-language-2025",
         "comparative-analysis-pretrained-2025",
         "comparative-review-ai-2024",
         "comparative-study-dsl-2024",
         "comparative-study-large-2025",
         "compass-contrastive-learning-2026",
         "competitive-programming-reasoning-models-2025",
         "compilable-neural-code-2022",
         "compiler-feedback-loops-2025",
         "compilernext-searchbased-compiler-2025",
         "completion-by-comprehension-2025",
         "complexcodeeval-benchmark-evaluating-2024",
         "compounding-reliability-2025",
         "comprehensive-analysis-machine-2025",
         "comprehensive-llm-secure-code-2025",
         "comprehensive-study-posttraining-2023",
         "comprehensive-survey-aidriven-2024",
         "comprehensive-survey-llm-2024",
         "comprehensive-survey-trustworthiness-2025",
         "comprehensive-taxonomy-hallucinations-2025",
         "comprehensive-verilog-design-2025",
         "compute-optimal-inference-2024",
         "concept-influence-leveraging-2026",
         "conceptguard-neurosymbolic-safety-2025",
         "concerned-data-contamination-2024",
         "concrete-roadmap-safety-2025",
         "condor-enhance-llm-2025",
         "confidencedriven-multiscale-model-2026",
         "confidenceguided-stepwise-model-2025",
         "configuring-agentic-coding-tools-2026",
         "conformal-constrained-policy-2025",
         "consistency-key-detecting-2025",
         "constitutional-ai-2022",
         "constrained-decoding-diffusion-2025",
         "constrained-decoding-fillinthemiddle-2024",
         "context-engineering-ai-2025",
         "contextaugmented-code-generation-2024",
         "contrastrepair-enhancing-conversationbased-2024",
         "control-models-inide-2026",
         "controlled-selfevolution-algorithmic-2026",
         "convergence-dynamics-agenttoagent-2025",
         "cooperbench-why-coding-2026",
         "copilot-arena-platform-2025",
         "copilot-code-quality-empirical-2023",
         "copilot-efficiency-real-world-2024",
         "copilot-evaluation-harness-2024",
         "copilot-longitudinal-case-study-2025",
         "copilot-productivity-controlled-2023",
         "copilot-security-weaknesses-2023",
         "copilot-zoominfo-productivity-2025",
         "copiloting-copilots-fusing-2023",
         "core-bench-computational-2024",
         "core-comprehensive-ontological-2026",
         "corecodebench-decoupling-code-2025",
         "correctnessguaranteed-code-generation-2025",
         "cosight-enhancing-llmbased-2025",
         "cost-accuracy-longterm-2026",
         "cost-dynamic-reasoning-2025",
         "cotbased-synthesizer-enhancing-2025",
         "cotdeceptoradversarial-code-obfuscation-2025",
         "cotrag-integrating-chain-2025",
         "cotran-llmbased-code-2023",
         "courtguard-local-multiagent-2025",
         "coverup-effective-high-2024",
         "cracking-sql-barriers-2025",
         "creativeval-evaluating-creativity-2024",
         "critical-evaluation-defenses-2025",
         "critical-review-large-2023",
         "crosscodeeval-diverse-multilingual-2023",
         "crossllm-generalization-behavioral-2025",
         "crossmodal-memory-compression-2026",
         "crossplatform-evaluation-large-2025",
         "crqbench-benchmark-code-2024",
         "crscore-reinforcement-learning-2025",
         "cruxeval-benchmark-code-2024",
         "cruxevalx-benchmark-multilingual-2024",
         "cuckoo-attack-stealthy-2025",
         "cudaforge-agent-framework-2025",
         "current-challenges-software-2024",
         "curriculum-guided-massive-2025",
         "cursor-speed-quality-tradeoff-2025",
         "cweval-outcomedriven-evaluation-2025",
         "dacode-agent-data-2024",
         "dancing-critiques-enhancing-2025",
         "dangers-poisoned-llms-2025",
         "dapo-opensource-llm-2025",
         "data-contamination-benchmarks-2023",
         "datasentinel-gametheoretic-detection-2025",
         "deep-dive-into-2024-2",
         "deep-rl-matters-2018",
         "deepreview-improving-llmbased-2025",
         "deepseek-coder-2024",
         "deepseek-coder-v2-2024",
         "deepseek-r1-2025",
         "deepseek-v3-2024",
         "defending-against-indirect-2024",
         "defense-against-prompt-2024",
         "dehallucinator-mitigating-llm-2024",
         "demystifying-llmbased-software-2025",
         "diffusionsdf-conditional-generative-2022",
         "diversity-empowers-intelligence-2024",
         "does-prompt-formatting-2024",
         "dont-complete-it-2022",
         "dont-overthink-it-2025",
         "dpo-superior-ppo-2024",
         "drawing-pandas-benchmark-2024",
         "drift-dynamic-rulebased-2025",
         "dspy-compiling-declarative-2023",
         "efficient-guided-generation-2023",
         "effilearner-enhancing-efficiency-2024",
         "emergent-abilities-large-2022",
         "emergent-abilities-mirage-2023",
         "empirical-evaluation-large-2025",
         "empirical-study-finetuning-2023",
         "empirical-study-retrievalaugmented-2025",
         "empirical-study-usage-2024",
         "engineering-multiagent-llms-2025",
         "enhancing-code-translation-2024",
         "evaluating-language-models-2024",
         "evocodebench-evolving-code-2024",
         "evomarl-coevolutionary-multiagent-2025",
         "evor-evolving-retrieval-2024",
         "executable-code-actions-2024",
         "experimental-evidence-productivity-2023",
         "exploring-generalizable-automated-2025",
         "exposing-privacy-gaps-2024",
         "fast-inference-from-2022",
         "fath-authenticationbased-testtime-2024",
         "formalizing-benchmarking-prompt-2023",
         "from-code-courtroom-2025",
         "from-llm-reasoning-2025",
         "frontier-models-in-context-scheming-2024",
         "frontiermath-benchmark-evaluating-2024",
         "fuzz4all-universal-fuzzing-2023",
         "gaia-benchmark-general-2023",
         "gamma-revisiting-templatebased-2023",
         "gans-created-equal-2018",
         "gemma-open-models-2024",
         "generative-agents-interactive-2023",
         "generative-ai-at-2023",
         "github-copilot-test-2024",
         "gorilla-large-language-2023",
         "gpqa-graduatelevel-googleproof-2023",
         "gpt4-technical-report-2023",
         "granite-code-models-2024",
         "graphcodeagent-dual-graphguided-2025",
         "graphcoder-enhancing-repositorylevel-2024",
         "grokking-generalization-beyond-2022",
         "guardian-multitiered-defense-2024",
         "guiding-llms-right-2024",
         "hallucination-by-code-2025",
         "hallucination-inevitable-innate-2024",
         "hallulens-llm-hallucination-2025",
         "hits-highcoverage-llmbased-2024",
         "how-effective-neural-2023",
         "how-much-does-2024",
         "how-should-i-2025",
         "hybrid-automated-program-2024",
         "hyperagent-generalist-software-2024",
         "identifying-mitigating-api-2025",
         "impact-code-language-2023",
         "impact-large-language-2024",
         "improving-factuality-reasoning-2023",
         "incontext-sharpness-as-2024",
         "indirect-prompt-injections-2025",
         "inference-scaling-laws-2024",
         "injecguard-benchmarking-mitigating-2024",
         "interactive-code-generation-2022",
         "intuition-to-evidence-productivity-2025",
         "invalidator-automated-patch-2023",
         "ipiguard-novel-tool-2025",
         "jailbreaking-safety-aligned-llms-2024",
         "jatmo-prompt-injection-2023",
         "judging-llmasajudge-mtbench-2023",
         "lamda-language-models-2022",
         "large-language-model-2024",
         "large-language-models-2023-3",
         "largescale-independent-comprehensive-2024",
         "leakage-code-generation-2024",
         "leakage-reproducibility-crisis-2023",
         "learn-code-sustainably-2024",
         "less-training-more-2022",
         "lessleakbench-first-investigation-2025",
         "lessons-from-trenches-2024",
         "lhdeception-simulating-understanding-2025",
         "linguistics-theory-meets-2024",
         "livebench-challenging-contaminationlimited-2024",
         "livecodebench-2024",
         "llama-3-herd-2024",
         "llama-open-efficient-2023",
         "llm-agents-se-survey-2024",
         "llm-code-review-benchmarking-2025",
         "llm-critics-help-2024",
         "llm-fuzzing-challenges-2024",
         "llm-hallucinations-code-practical-2024",
         "llm-long-term-memory-eval-2024",
         "llm-strategic-deception-under-pressure-2023",
         "llm-unit-test-generation-empirical-2024",
         "llmailinject-dataset-from-2025",
         "llmassisted-static-analysis-2024",
         "llmbased-retrievalaugmented-control-2024",
         "llmcoordination-evaluating-analyzing-2023",
         "llms-se-systematic-review-2023",
         "lost-middle-how-2023",
         "lost-mix-evaluating-2025",
         "lost-translation-study-2024",
         "lpcd-unified-framework-2025",
         "lutllm-efficient-large-2025",
         "lynx-open-source-2024",
         "mactg-multiagent-collaborative-2024",
         "madspear-conformitydriven-prompt-2025",
         "maestro-multiagent-evaluation-2026",
         "magentic-marketplace-opensource-2025",
         "magenticone-generalist-multiagent-2024",
         "magicoder-source-code-2023",
         "malice-agentland-down-2025",
         "manipulating-multimodal-agents-2025",
         "mapcoder-multiagent-code-2024",
         "masai-modular-architecture-2024",
         "matplotagent-method-evaluation-2024",
         "mcp-safety-audit-2025",
         "measuring-agents-production-2025",
         "measuring-ai-ability-2025",
         "melon-provable-defense-2025",
         "memgpt-llms-as-2023",
         "mercury-efficiency-benchmark-2024",
         "metagpt-multi-agent-framework-2023",
         "metr-rct-2025",
         "mind2web-generalist-agent-2023",
         "mitigating-api-hallucination-2025",
         "mlebench-evaluating-machine-2024",
         "mmlu-measuring-massive-2020",
         "moco-onestop-shop-2026",
         "monitorguided-decoding-code-2023",
         "more-llm-calls-2024",
         "multi-agent-collaboration-survey-2025",
         "multiagent-risks-from-2025",
         "multiple-scalable-polyglot-2023",
         "navigating-complexity-generative-2023",
         "neural-exec-learning-2024",
         "neurips-reproducibility-2021",
         "nlp-evaluation-trouble-2023",
         "no-more-manual-2023",
         "no-need-lift-2023",
         "not-what-youve-2023",
         "openhands-ai-sw-agent-2024",
         "optima-optimizing-effectiveness-2024",
         "optimizationbased-prompt-injection-2024",
         "osworld-benchmarking-multimodal-2024",
         "palm-scaling-language-2022",
         "paperbench-evaluating-ais-2025",
         "performance-study-llmgenerated-2024",
         "phi4-technical-report-2024",
         "plan-and-act-long-horizon-2025",
         "poisoning-attacks-llms-2025",
         "preventing-rogue-agents-2025",
         "productivity-assessment-neural-2022",
         "projecteval-benchmark-programming-2025",
         "promises-perils-timely-2026",
         "prompt-infection-llmtollm-2024",
         "prompt-injection-attacks-2024",
         "prompt-injection-llm-apps-2023",
         "promptarmor-simple-yet-2025",
         "quantifying-contamination-evaluating-2024",
         "questionable-practices-ml-2024",
         "qwen25-technical-report-2024",
         "qwen25coder-technical-report-2024",
         "ragtruth-hallucination-corpus-2023",
         "rapgen-retrievalaugmented-patch-2023",
         "reacc-retrievalaugmented-code-2022",
         "react-synergizing-reasoning-2022",
         "rebench-evaluating-frontier-2024",
         "redcode-risky-code-2024",
         "reflexion-language-agents-2023",
         "repairagent-llm-bug-repair-2024",
         "repairllama-efficient-representations-2023",
         "repoaudit-autonomous-llmagent-2025",
         "repocoder-repositorylevel-code-2023",
         "repoformer-selective-retrieval-2024",
         "reproducibility-ml-overview-2025",
         "rethinking-benchmark-contamination-2023",
         "rethinking-verification-llm-2025",
         "retrievalaugmented-code-generation-2025",
         "rise-ai-teammates-2025",
         "rise-potential-large-2023",
         "rlcoder-reinforcement-learning-2024",
         "rltf-reinforcement-learning-2023",
         "runbugrun-executable-dataset-2023",
         "scaffolded-model-capability-2023",
         "scaling-laws-2020",
         "secalign-defending-against-2024",
         "secodeplt-unified-platform-2024",
         "security-degradation-iterative-2025",
         "self-instruct-aligning-language-2022",
         "selfcheckgpt-zeroresource-blackbox-2023",
         "selfconsistency-improves-chain-2022",
         "semcoder-training-code-2024",
         "show-your-work-2019",
         "sirens-song-ai-2023",
         "sleeper-agents-2024",
         "sloaware-gpu-dvfs-2024",
         "smoothquant-accurate-efficient-2022",
         "software-engineering-by-2025",
         "soleval-benchmarking-large-2025",
         "sparks-agi-early-2023",
         "starcoder-2023",
         "starcoder2-2024",
         "survey-automated-program-2023",
         "survey-autonomous-llm-agents-2023",
         "survey-code-gen-llm-agents-2025",
         "survey-hallucination-large-2023-2",
         "survey-large-language-2023",
         "survey-learningbased-automated-2023",
         "survey-llm-code-generation-2025",
         "swe-agent-2024",
         "swe-bench-2023",
         "swe-bench-plus-2024",
         "swe-bench-pro-2025",
         "swelancer-can-frontier-2025",
         "swerebench-automated-pipeline-2025",
         "swtbench-testing-validating-2024",
         "syncode-llm-generation-2024",
         "syntaxaware-onthefly-code-2022",
         "systematic-literature-review-2024",
         "tales-from-trenches-2024",
         "task-shield-enforcing-2024",
         "test-driven-interactive-code-gen-2024",
         "test-smells-llmgenerated-2024",
         "testdriven-development-llmbased-2024",
         "testgeneval-real-world-2024",
         "think-deep-think-2025",
         "thinking-llms-lie-2025",
         "tigercoder-novel-suite-2025",
         "toolformer-language-models-2023",
         "toolllm-facilitating-large-2023",
         "top-leaderboard-ranking-2024",
         "tree-thoughts-deliberate-2023",
         "troubling-trends-ml-2018",
         "trust-ai-benchmarks-2025",
         "trustworthy-llm-agents-survey-2025",
         "uc-berkeley-mast-2025",
         "understanding-software-engineering-2025",
         "unified-scaling-laws-2022",
         "unsupervised-realtime-hallucination-2024",
         "verilogeval-evaluating-large-2023",
         "verimind-agentic-llm-2025",
         "vibe-coding-practice-2025",
         "visualwebarena-evaluating-multimodal-2024",
         "voyager-open-ended-2023",
         "wasp-benchmarking-web-2025",
         "webarena-autonomous-agents-2023",
         "webbench-llm-code-2025",
         "what-wrong-your-2024",
         "when-singleagent-skills-2026",
         "where-do-ai-2026",
         "which-agent-causes-2025",
         "wizardcoder-empowering-code-2023",
         "your-code-generated-2023"
       ],
       [
         "automated-program-repair-2023-3",
         "automated-program-repair-2024-3",
         "automated-program-repair-2025-2"
       ],
       [
         "beyond-hype-comprehensive-2024",
         "how-beginning-programmers-2024",
         "how-far-we-2023"
       ],
       [
         "2025-ai-agent-2026",
         "remote-labor-index-2025"
       ],
       [
         "artificial-intelligence-system-2024",
         "comparative-study-ai-2025"
       ],
       [
         "coprompter-usercentric-evaluation-2024",
         "who-validates-validators-2024"
       ],
       [
         "caredio-cultural-alignment-2025",
         "unintended-impacts-llm-2024"
       ],
       [
         "collab-controlled-decoding-2025",
         "transfer-q-star-2024"
       ],
       [
         "ai-inference-falling-costs-2025",
         "intelligence-per-watt-2025"
       ],
       [
         "analysis-research-status-2025",
         "utboost-rigorous-evaluation-2025"
       ],
       [
         "combined-approach-program-2024",
         "unified-multitask-learning-2022"
       ],
       [
         "bioragent-retrievalaugmented-generation-2024",
         "gemini-15-technical-report-2024"
       ]
     ]
   }
 }