GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning

Recent advances in general medical AI have made significant strides, but existing models often lack the reasoning capabilities needed for complex medical decision-making. This paper presents GMAI-VL-R1, a multimodal medical reasoning model enhanced by reinforcement learning (RL) to improve its reasoning abilities. Through iterative training, GMAI-VL-R1 optimizes decision-making, significantly boosting diagnostic accuracy and clinical support. We also develop a reasoning data synthesis method, generating step-by-step reasoning data via rejection sampling, which further enhances the model's generalization. Experimental results show that after RL training, GMAI-VL-R1 excels in tasks such as medical image diagnosis and visual question answering. While the model demonstrates basic memorization with supervised fine-tuning, RL is crucial for true generalization. Our work establishes new evaluation benchmarks and paves the way for future advancements in medical reasoning models. Code, data, and model will be released at \href{this https URL}{this link}.

@article{su2025_2504.01886,
  title={ GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning },
  author={ Yanzhou Su and Tianbin Li and Jiyao Liu and Chenglong Ma and Junzhi Ning and Cheng Tang and Sibo Ju and Jin Ye and Pengcheng Chen and Ming Hu and Shixiang Tang and Lihao Liu and Bin Fu and Wenqi Shao and Xiaowei Hu and Xiangwen Liao and Yuanfeng Ji and Junjun He },
  journal={arXiv preprint arXiv:2504.01886},
  year={ 2025 }
}