Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning

Documenti analoghi

• Stable and Efficient Single-Rollout RL for Multimodal Reasoning
  di: Liu, Rui, et al.
  Pubblicazione: (2025)
• Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning
  di: Liang, Zhenwen, et al.
  Pubblicazione: (2025)
• Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data
  di: Liang, Zhenwen, et al.
  Pubblicazione: (2026)
• Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis
  di: Shi, Yucheng, et al.
  Pubblicazione: (2026)
• Group Distributionally Robust Optimization-Driven Reinforcement Learning for LLM Reasoning
  di: Panaganti, Kishan, et al.
  Pubblicazione: (2026)