Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Haolin, Yu, Dian, Lu, Sidi, Zhou, Yujun, Liu, Rui, Liang, Zhenwen, Mi, Haitao, Wei, Chen-Yu, Yu, Dong
Format:	Preprint
Published:	2026
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/2601.18984