ai-research-survey

Systematic scan of agentic development research. What's signal, what's noise.
git clone https://git.shiptheloop.com/ai-research-survey.git
Log | Files | Refs

paper_type.json (290B)


      1 {
      2   "paper_type": "empirical",
      3   "reason": "Runs experiments comparing LLMs (GPT-4, GPT-3.5, Code Llama, WizardCoder) on existing benchmarks (HumanEval, MBPP, LeetCode) and reports quantitative findings about code efficiency, correctness-efficiency correlation, and prompting strategies."
      4 }

Impressum · Datenschutz