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 (345B)


      1 {
      2   "paper_type": "empirical",
      3   "reason": "Runs experiments evaluating LLM performance on hierarchical legal reasoning, reports quantitative results (100% on surface-level vs 11-34% on integrated analysis, 2.6x RL improvement), with primary contribution being empirical findings about the thinking-longer paradox rather than a new benchmark."
      4 }

Impressum · Datenschutz