@article{semioffpolicyreinforcementlearningforvis,
  title = {Semi-off-Policy Reinforcement Learning for Vision-Language Slow-Thinking Reasoning},
  author = {Junhao Shen and Haiteng Zhao and Yuzhe Gu and Songyang Gao and Kuikun Liu and Haian Huang and Jianfei Gao and Dahua Lin and Wenwei Zhang and Kai Chen},
  year = {2025},
  eprint = {2507.16814},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.16814},
}