PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering

Documenti analoghi

• R-Align: Enhancing Generative Reward Models through Rationale-Centric Meta-Judging
  di: Lai, Yanlin, et al.
  Pubblicazione: (2026)
• WebVR: Benchmarking Multimodal LLMs for WebPage Recreation from Videos via Human-Aligned Visual Rubrics
  di: Dai, Yuhong, et al.
  Pubblicazione: (2026)
• Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
  di: Hu, Jingcheng, et al.
  Pubblicazione: (2025)
• EngTrace: A Symbolic Benchmark for Verifiable Process Supervision of Engineering Reasoning
  di: Gull, Ayesha, et al.
  Pubblicazione: (2025)
• Thinking by Doing: Building Efficient World Model Reasoning in LLMs via Multi-turn Interaction
  di: Shu, Bao, et al.
  Pubblicazione: (2025)