Deep Dense Exploration for LLM Reinforcement Learning via Pivot-Driven Resampling

Documenti analoghi

• Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models
  di: Guo, Yiran, et al.
  Pubblicazione: (2025)
• CodePivot: Bootstrapping Multilingual Transpilation in LLMs via Reinforcement Learning without Parallel Corpora
  di: Li, Shangyu, et al.
  Pubblicazione: (2026)
• Comments as Natural Logic Pivots: Improve Code Generation via Comment Perspective
  di: Chen, Yijie, et al.
  Pubblicazione: (2024)
• DeepTrans: Deep Reasoning Translation via Reinforcement Learning
  di: Wang, Jiaan, et al.
  Pubblicazione: (2025)
• Back to Basics: Revisiting Exploration in Reinforcement Learning for LLM Reasoning via Generative Probabilities
  di: Li, Pengyi, et al.
  Pubblicazione: (2026)