@article{cpmobiusiterativecoachplayerreasoningfor, title = {CPMobius: Iterative Coach-Player Reasoning for Data-Free Reinforcement Learning}, author = {Ran Li and Zeyuan Liu and Yinghao Chen and Bingxiang He and Jiarui Yuan and Zixuan Fu and Weize Chen and Jinyi Hu and Chen Qian and Zhiyuan Liu and Maosong Sun}, year = {2026}, eprint = {2602.02979}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.02979}, }