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 (325B)


      1 {
      2   "paper_type": "benchmark-creation",
      3   "reason": "Introduces DyCodeEval, a new dynamic benchmarking framework with a four-agent pipeline for generating contamination-resistant test variants, plus a novel DyPass@K metric; experiments validate the benchmark's robustness rather than constituting the primary contribution."
      4 }

Impressum · Datenschutz