From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jiang, Yuxin, Wang, Yufei, Zhang, Qiyuan, Zeng, Xingshan, Li, Liangyou, Chen, Jierun, Tao, Chaofan, Bai, Haoli, Shang, Lifeng
Format:	Preprint
Published:	2026
Subjects:	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/2601.18533