Internalize the Temperature: On-Policy Self-Distillation as Policy Reheater for Reinforcement Learning

Documenti analoghi

• S2J: Bridging the Gap Between Solving and Judging Ability in Generative Reward Models
  di: Sun, Shaoning, et al.
  Pubblicazione: (2025)
• LoCa: Logit Calibration for Knowledge Distillation
  di: Yang, Runming, et al.
  Pubblicazione: (2024)
• Think-with-Rubrics: From External Evaluator to Internal Reasoning Guidance
  di: Yu, Jiachen, et al.
  Pubblicazione: (2026)
• Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
  di: Zhao, Siyan, et al.
  Pubblicazione: (2026)
• Look Inward to Explore Outward: Learning Temperature Policy from LLM Internal States via Hierarchical RL
  di: Zhou, Yixiao, et al.
  Pubblicazione: (2026)