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 (323B)


      1 {
      2   "paper_type": "empirical",
      3   "reason": "Runs experiments on 900 agentic execution traces across three LLMs, reports quantitative performance metrics (e.g., 2/30 accuracy), and contributes experimental findings about failure archetypes rather than introducing a novel benchmark or dataset as the primary contribution."
      4 }

Impressum · Datenschutz