When Reward Hacking Rebounds: Understanding and Mitigating It with Representation-Level Signals

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Rui, Tang, Ruixiang
Format:	Preprint
Published:	2026
Subjects:	Machine Learning 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/2604.01476