arXiv:2505.03335 · 中英对照阅读

Absolute Zero: Reinforced Self-play Reasoning with Zero Data

Andrew Zhao, Yiran Wu, Yang Yue, Tong Wu, Quentin Xu, Yang Yue, Matthieu Lin, Shenzhi Wang, Qingyun Wu, Zilong Zheng, Gao Huang

摘要

marginparsep has been altered. topmargin has been altered. marginparpush has been altered.