DeCoRL: Decoupling Reasoning Chains via Parallel Sub-Step Generation and Cascaded Reinforcement for Interpretable and Scalable RLHF

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gao, Ziyuan, Liang, Di, Wu, Xianjie, Morel, Philippe, Peng, Minlong
Format:	Preprint
Published:	2025
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/2511.19097