StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Daoyu, Li, Qingchuan, Cheng, Mingyue, Ouyang, Jie, Yu, Shuo, Liu, Qi, Chen, Enhong
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/2604.18401