SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huo, Yifu, Wang, Chenglong, Zhu, Ziming, Xing, Shunjie, Feng, Peinan, Liu, Tongran, He, Qiaozhi, Zhou, Tianhua, Chang, Xiaojia, Zhu, Jingbo, Yu, Zhengtao, Xiao, Tong
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.16995