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 (316B)


      1 {
      2   "paper_type": "benchmark-creation",
      3   "reason": "Introduces SWE-MERA, a new dynamic benchmark for evaluating LLMs on software engineering tasks with ~10,000 tasks via automated pipeline; experimental results validate the benchmark's discriminative power but are secondary to the benchmark contribution itself."
      4 }

Impressum · Datenschutz