@article{textm3texthfmultiagentreinforcement, title = {M3HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality}, author = {Ziyan Wang and Zhicheng Zhang and Fei Fang and Yali Du}, year = {2025}, eprint = {2503.02077}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.02077v3}, }