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 (267B)


      1 {
      2   "paper_type": "empirical",
      3   "reason": "Conducts continuous evaluation experiments measuring LLM forecasting accuracy over time, reporting quantitative performance degradation results (21.55%, 11.33%) and testing interventions like RAG and gold article access."
      4 }

Impressum · Datenschutz