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 (332B)


      1 {
      2   "paper_type": "empirical",
      3   "reason": "Reports quantitative experimental results (90–100% coverage, iteration counts) comparing GPT-3.5 and GPT-4 performance on testbench generation and bug detection tasks across FSM cases, with the primary contribution being the empirical findings about iterative feedback effectiveness."
      4 }

Impressum · Datenschutz