Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2510.18424 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915566494679040 |
|---|---|
| author | Guo, Guangfu Lu, Xiaoqian Feng, Yue |
| author_facet | Guo, Guangfu Lu, Xiaoqian Feng, Yue |
| contents | Visual 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-VRAgent 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_18424 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Med-VRAgent: A Framework for Medical Visual Reasoning-Enhanced Agents Guo, Guangfu Lu, Xiaoqian Feng, Yue Artificial Intelligence Visual 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-VRAgent 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. |
| title | Med-VRAgent: A Framework for Medical Visual Reasoning-Enhanced Agents |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2510.18424 |