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 (373B)


      1 {
      2   "paper_type": "empirical",
      3   "reason": "Primary contribution is experimental findings on task scaling: showing that increasing task count from 8 to 512 consistently improves reasoning performance and training efficiency, with SOTA results on benchmarks, while InternBootcamp framework and BOOTCAMP-EVAL are the experimental infrastructure rather than the main focus."
      4 }

Impressum · Datenschutz