@article{rewardreasoningmodel, title = {Reward Reasoning Model}, author = {Jiaxin Guo and Zewen Chi and Li Dong and Qingxiu Dong and Xun Wu and Shaohan Huang and Furu Wei}, year = {2025}, eprint = {2505.14674}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.14674v1}, }