@article{adversarialrewardauditingforactivedetect, title = {Adversarial Reward Auditing for Active Detection and Mitigation of Reward Hacking}, author = {Mohammad Beigi and Ming Jin and Junshan Zhang and Qifan Wang and Lifu Huang}, year = {2026}, eprint = {2602.01750}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.01750}, }