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 (306B)


      1 {
      2   "paper_type": "benchmark-creation",
      3   "reason": "Paper introduces an improved evaluation framework (UTBoost parser) with corrected benchmark data, identifying and fixing annotation errors in SWE-Bench; primary contribution is the improved benchmark infrastructure, not findings about agent behavior."
      4 }

Impressum · Datenschutz