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 (334B)


      1 {
      2   "paper_type": "benchmark-creation",
      3   "reason": "Introduces SWE-rebench, an automated pipeline that extracts 21,336 verifiable tasks from GitHub to create a new decontaminated benchmark for evaluating software engineering agents; the primary contribution is the benchmark and pipeline infrastructure, not experimental findings."
      4 }

Impressum · Datenschutz