Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Guanhua, Xu, Tingqiang, Wang, Mingze, Yi, Qi, Gong, Xue, Li, Siheng, Xiong, Ruibin, Li, Kejiao, Jiang, Yuhao, Zhou, Bo
Format:	Preprint
Published:	2025
Subjects:	Machine Learning 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/2510.03222