Vision language models (VLMs) achieve strong performance on general image understanding but struggle to think with medical images, especially when performing multi-step reasoning through iterative visual interaction. Medical VLMs often rely on static visual embeddings and single-pass inference, preventing models from re-examining, verifying, or refining visual evidence during reasoning. While tool-integrated reasoning offers a promising path forward, open-source VLMs lack the training infrastructure to learn effective tool selection, invocation, and coordination in multi-modal medical reasoning. We introduce MedVistaGym, a scalable and interactive training environment that incentivizes tool-integrated visual reasoning for medical image analysis. MedVistaGym equips VLMs to determine when and which tools to invoke, localize task-relevant image regions, and integrate single or multiple sub-image evidence into interleaved multimodal reasoning within a unified, executable interface for agentic training. Using MedVistaGym, we train MedVistaGym-R1 to interleave tool use with agentic reasoning through trajectory sampling and end-to-end reinforcement learning. Across six medical VQA benchmarks, MedVistaGym-R1-8B exceeds comparably sized tool-augmented baselines by 19.10% to 24.21%, demonstrating that structured agentic training--not tool access alone--unlocks effective tool-integrated reasoning for medical image analysis.

翻译：视觉语言模型在通用图像理解任务上表现出色，但在处理医学图像时，尤其在需要通过迭代视觉交互进行多步推理的场景中，仍面临显著挑战。现有的医学视觉语言模型通常依赖于静态视觉嵌入和单次推理机制，导致模型在推理过程中无法对视觉证据进行重新审视、验证或优化。尽管工具集成推理为这一领域提供了有前景的发展路径，但开源视觉语言模型目前缺乏相应的训练基础设施，难以在多模态医学推理中学习有效的工具选择、调用与协调策略。为此，我们提出了MedVistaGym——一个可扩展的交互式训练环境，旨在促进面向医学图像分析的工具集成视觉推理。MedVistaGym赋予视觉语言模型以下能力：判断何时调用何种工具、定位任务相关的图像区域，并将单个或多个子图像证据整合到交错的多模态推理流程中，所有操作均在统一的、可执行的智能体训练接口中完成。基于MedVistaGym，我们通过轨迹采样与端到端强化学习方法训练了MedVistaGym-R1模型，使其能够将工具使用与智能体推理过程交错结合。在六项医学视觉问答基准测试中，MedVistaGym-R1-8B模型相较于同等规模的工具增强基线模型，性能提升了19.10%至24.21%。这一结果表明，结构化智能体训练——而非单纯提供工具访问权限——才是解锁医学图像分析中高效工具集成推理能力的关键。