@inproceedings{guo-etal-2025-med,
    title = "{M}ed-{VRA}gent: A Framework for Medical Visual Reasoning-Enhanced Agents",
    author = "Guo, Guangfu  and
      Lu, Xiaoqian  and
      Feng, Yue",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.emnlp-main.939/",
    doi = "10.18653/v1/2025.emnlp-main.939",
    pages = "18613--18627",
    ISBN = "979-8-89176-332-6",
    abstract = "Vision-language models (VLMs) achieve promising results in medical reasoning but struggle with hallucinations, vague descriptions, Inconsistent logic and poor localization. To address this, we propose a agent framework named Medical Visual Reasoning Agent (\textbf{Med-VRAgent}). The approach is based on Visual Guidance and Self-Reward paradigms and Monte Carlo Tree Search (MCTS). By combining the Visual Guidance with tree search, Med-VRAgent improves the medical visual reasoning capabilities of VLMs. We use the trajectories collected by Med-RAgent as feedback to further improve the performance by fine-tuning the VLMs with the proximal policy optimization (PPO) objective. Experiments on multiple medical VQA benchmarks demonstrate that our method outperforms existing approaches."
}