@article{reinforcementlearningforlargemodelasurve, title = {Reinforcement Learning for Large Model: A Survey}, author = {Weijia Wu and Chen Gao and Joya Chen and Kevin Qinghong Lin and Qingwei Meng and Yiming Zhang and Yuke Qiu and Hong Zhou and Mike Zheng Shou}, year = {2025}, eprint = {2508.08189}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.08189}, }