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 (380B)


      1 {
      2   "paper_type": "empirical",
      3   "reason": "The paper runs systematic experiments with LLM agents on microservice specifications, reports quantitative performance metrics (83-94% unit test pass rates), and evaluates different approaches (fine-grained vs service-level code generation, reflection strategies) across models, making experimental findings the primary contribution."
      4 }

Impressum · Datenschutz