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 (304B)


      1 {
      2   "paper_type": "empirical",
      3   "reason": "Proposes a type-constrained decoding method and reports quantitative experimental results (50-75% error reduction, 3.5-37% improvement in pass@1) across 6 LLMs on existing benchmarks (HumanEval, MBPP), with primary contribution being the empirical findings."
      4 }

Impressum · Datenschutz