Author

Xiaozhi Wang

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

CATCH: A Controllable Analysis Testbed for Reward Hacking in Coding RL

During reinforcement learning with verifiable rewards (RLVR), large language models (LLMs) can exploit loopholes in their environments to obtain high rewards without improving the intended capabilities, i.e., reward hacking. Despite its risks to training efficiency and safety, monitoring and mitigating reward hacking d...

Shou-Li Wang, Yan-Feng Jia, Zhi-Hao Ou et al. · 0 citations

#artificial intelligence Jun 2026

Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning

CHERRL is introduced, a Controllable Hacking Environment for Rubric-based RL that enables stable reproduction of reward hacking, explicit observation of reward divergence, and identification of hacking onset and analyzes different judge biases from the perspectives of discoverability and exploitability.

Xuekang Wang, Zhuoyuan Hao, Shuo Hou et al. · arXiv.org · 10 citations · ⚡1