Hybrid Reward Normalization for Process-supervised Non-verifiable Agentic Tasks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Peiran, Li, Zhuohao, Xing, Xiaoying, Zhang, Guannan, Li, Debiao, Shi, Kunyu
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2509.25598