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 (277B)


      1 {
      2   "paper_type": "benchmark-creation",
      3   "reason": "Introduces GitTaskBench, a new 54-task benchmark for evaluating code agents across 7 domains; the benchmark itself is the primary contribution, with experimental evaluation of baselines serving to demonstrate its utility."
      4 }

Impressum · Datenschutz