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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Xiaoyun, Yuan, Xiaojian, Huang, Di, You, Wang, Hu, Chen, Ruan, Jingqing, Jian, Ai, Chen, Kejiang, Hu, Xing
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2510.10959