SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning

@misc{zhang2025srpoenhancingmultimodal,
      title={SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware  Reinforcement Learning},
      author={Yu Zhang and Yangfan He and Yifan Jiang and Che Liu and Jing Xiong and Mi Zhang and Zhongwei Wan and Shen Yan and Yi Xin and Hui Shen and Zhihao Dou and Dongfei Cui and Qinjian Zhao},
      year={2025},
      eprint={2506.01713},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2506.01713},
}