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 (301B)


      1 {
      2   "paper_type": "benchmark-creation",
      3   "reason": "The primary contribution is the Who&When dataset with 184 annotated failure tasks and formalization of the automated failure attribution task; the evaluation of three attribution methods serves to validate the benchmark's difficulty and utility."
      4 }

Impressum · Datenschutz