@article{absolutezeroreinforcedselfplayreasoning, title = {Absolute Zero: Reinforced Self-play Reasoning with Zero Data}, author = {Andrew Zhao and Yiran Wu and Tong Wu and Quentin Xu and Yang Yue and Matthieu Lin and Shenzhi Wang and Qingyun Wu and Zilong Zheng and Gao Huang}, year = {2025}, eprint = {2505.03335}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.03335v2}, }