Breaking Contextual Inertia: Reinforcement Learning with Single-Turn Anchors for Stable Multi-Turn Interaction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Xingwu, Zhang, Zhanqiu, Guo, Yiwen, Zou, Difan
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence 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/2603.04783