Skip to content
星际流动

Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning

发布
采集
学术前沿 6.7 分 — Adaptive coefficient unlocks entropy regularization potential for RLVR
原文: cs.CL updates on arXiv.org

评分 6.7 · 来源:cs.CL updates on arXiv.org · 发布于 2026-04-20

评分依据:Adaptive coefficient unlocks entropy regularization potential for RLVR