Do Synthetic Trajectories Reflect Real Reward Hacking? A Systematic Study on Monitoring In-the-Wild Hacking in Code Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Lichen, Zhou, Hengguang, Liang, Yijun, Zhou, Tianyi, Hsieh, Cho-Jui
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.23488