@article{mogrpomitigatingrewardhackingofgrouprela, title = {MO-GRPO: Mitigating Reward Hacking of Group Relative Policy Optimization on Multi-Objective Problems}, author = {Yuki Ichihara and Yuu Jinnai and Tetsuro Morimura and Mitsuki Sakamoto and Ryota Mitsuhashi and Eiji Uchibe}, year = {2025}, eprint = {2509.22047}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.22047}, }