Reinforcement Learning on Pre-Training Data

@misc{li2025reinforcementlearningpretraining,
      title={Reinforcement Learning on Pre-Training Data},
      author={Siheng Li and Kejiao Li and Zenan Xu and Guanhua Huang and Evander Yang and Kun Li and Haoyuan Wu and Jiajia Wu and Zihao Zheng and Chenchen Zhang and Kun Shi and Kyrierl Deng and Qi Yi and Ruibin Xiong and Tingqiang Xu and Yuhao Jiang and Jianfeng Yan and Yuyuan Zeng and Guanghui Xu and Jinbao Xue and Zhijiang Xu and Zheng Fang and Shuai Li and Qibin Liu and Xiaoxue Li and Zhuoyu Li and Yangyu Tao and Fei Gao and Cheng Jiang and Bo Chao Wang and Kai Liu and Jianchen Zhu and Wai Lam and Wayyt Wang and Bo Zhou and Di Wang},
      year={2025},
      eprint={2509.19249},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2509.19249},
}