arXiv:2608.30724v1 Announce Type: cross
Abstract: LLM agents are increasingly used to run autonomous ML experiments, iterating on target metrics with little human oversight. Prior work has documented...
By Pradyumna Shyama Prasad, Meiri Anto, Leon Eshuijs, Julian Moncarz, Kaustubh Kislay, Juan J. Vazquez
arXiv:2609.36308v1 Announce Type: new
Abstract: Reinforcement learning has helped AI agents solve increasingly difficult tasks, but high rewards do not always reflect the work users intended. In rece...
By Long Phan, Stephen K. Yang, Jason J. Lim, Mantas Mazeika, Wenyu Zhang, Zheyuan Liu, Richard Ren, Jingxiang Meng, Yaoteng Tan, Weiliang Zhao, Addison Wu, Matei Anghel, Dan Hendrycks
arXiv:2605.21384v2 Announce Type: replace-cross
Abstract: As long-horizon coding agents produce more code than any developer can review, oversight collapses onto a single surface: the automated test...
By Bingchen Zhao, Dhruv Srikanth, Yuxiang Wu, Zhengyao Jiang
arXiv:2609.39533v1 Announce Type: new
Abstract: During reinforcement learning with verifiable rewards (RLVR), large language models (LLMs) can exploit loopholes in their environments to obtain high r...
By Shouli Wang, Yanfeng Jia, Zhihao Ou, Zitao Su, Ruize He, Haotong Xie, Hao Peng, Juanzi Li, Xiaozhi Wang
arXiv:2606. 04923v1 Announce Type: cross Abstract: Rubric-based reinforcement learning (RL) uses an LLM-as-a-Judge (LaaJ) to score model outputs according to rubrics as rewards.
By Xuekang Wang, Zhuoyuan Hao, Shuo Hou, Hao Peng, Juanzi Li, Xiaozhi Wang
The paper introduces Gradient Fingerprint (GRIFT), a technique that uses a model’s internal gradient computations to detect reward hacking in reinforcement learning with verifiable rewards. GRIFT compresses gradients of a chain-of-thought (CoT) conditioned on a prompt into a compact representation, which is then used to assess whether the CoT reflects reward hacking. Experiments on math, code, and logical reasoning benchmarks show GRIFT outperforms baselines by over 25% and, when integrated into a rejection fine‑tuning pipeline, reduces reward hacking while improving task performance.
By Songtao Wang, Quang Hieu Pham, Fangcong Yin, Xinpeng Wang, Jocelyn Qiaochu Chen, Greg Durrett, Xi Ye