MEDVISTAGYM: A Scalable Training Environment for Thinking with Medical Images via Tool-Integrated Reinforcement Learning

• URL: http://arxiv.org/abs/2601.07107v1
• Date: Mon, 12 Jan 2026 00:11:10 GMT
• Title: MEDVISTAGYM: A Scalable Training Environment for Thinking with Medical Images via Tool-Integrated Reinforcement Learning
• Authors: Meng Lu, Yuxing Lu, Yuchen Zhuang, Megan Mullins, Yang Xie, Guanghua Xiao, Charles Fleming, Wenqi Shi, Xuan Wang,
• Abstract summary: Vision language models (VLMs) achieve strong performance on general image understanding but struggle to think with medical images.<n>We introduce MedVistaGym, a scalable and interactive training environment that incentivizes tool-integrated visual reasoning for medical image analysis.
• Score: 25.75780053067891
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning [53.37068897861388]
  MedSAM-Agent is a framework that reformulates interactive segmentation as a multi-step autonomous decision-making process.<n>We develop a two-stage training pipeline that integrates multi-turn, end-to-end outcome verification.<n>Experiments across 6 medical modalities and 21 datasets demonstrate that MedSAM-Agent achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-02-03T09:47:49Z)
• Incentivizing Tool-augmented Thinking with Images for Medical Image Analysis [35.90026194642237]
  We introduce Ophiuchus, a versatile, tool-augmented framework that equips an MLLM to decide when additional visual evidence is needed.<n>Our approach illuminates a path toward medical AI agents that can genuinely "think with images" through tool-integrated reasoning.
  arXiv  Detail & Related papers  (2025-12-16T07:37:23Z)
• Training Multi-Image Vision Agents via End2End Reinforcement Learning [51.81337984526068]
  We propose IMAgent, an open-source vision agent trained via end-to-end reinforcement learning.<n>By leveraging a multi-agent system, we generate challenging and visually-rich multi-image QA pairs.<n>We develop two specialized tools for visual reflection and confirmation, allowing the model to proactively reallocate its attention to image content.
  arXiv  Detail & Related papers  (2025-12-05T10:02:38Z)
• Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs [76.47326680870783]
  We introduce VISTA-Gym, a training environment for incentivizing tool-integrated visual reasoning capabilities in vision-language models (VLMs)<n> VISTA-Gym unifies diverse real-world multimodal reasoning tasks with a standardized interface for visual tools.<n>We show that VISTA-R1-8B outperforms state-of-the-art baselines with similar sizes by 9.51%-18.72% in 11 public reasoning-intensive VQA benchmarks.
  arXiv  Detail & Related papers  (2025-11-24T22:58:26Z)
• Think Twice to See More: Iterative Visual Reasoning in Medical VLMs [21.083636394814217]
  We introduce ViTAR, a framework that emulates the iterative reasoning process of human experts through a cognitive chain of "think-act-rethink-answer"<n>ViTAR treats medical images as interactive objects, enabling models to engage multi-step visual reasoning.
  arXiv  Detail & Related papers  (2025-10-11T06:39:57Z)
• GEMeX-RMCoT: An Enhanced Med-VQA Dataset for Region-Aware Multimodal Chain-of-Thought Reasoning [60.03671205298294]
  Medical visual question answering aims to support clinical decision-making by enabling models to answer natural language questions based on medical images.<n>Current methods still suffer from limited answer reliability and poor interpretability.<n>This work first proposes a Region-Aware Multimodal Chain-of-Thought dataset, in which the process of producing an answer is preceded by a sequence of intermediate reasoning steps.
  arXiv  Detail & Related papers  (2025-06-22T08:09:58Z)
• MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations [13.991376926757036]
  We propose MedUnifier, a unified Vision-Language Pre-Training framework tailored for medical data.<n>MedUnifier seamlessly integrates text-grounded image generation capabilities with multi-modal learning strategies.<n>Our approach employs visual vector quantization, which not only facilitates a more cohesive learning strategy for cross-modal understanding but also enhances multi-modal generation quality.
  arXiv  Detail & Related papers  (2025-03-02T21:09:32Z)
• Dr-LLaVA: Visual Instruction Tuning with Symbolic Clinical Grounding [53.629132242389716]
  Vision-Language Models (VLM) can support clinicians by analyzing medical images and engaging in natural language interactions. VLMs often exhibit "hallucinogenic" behavior, generating textual outputs not grounded in contextual multimodal information. We propose a new alignment algorithm that uses symbolic representations of clinical reasoning to ground VLMs in medical knowledge.
  arXiv  Detail & Related papers  (2024-05-29T23:19:28Z)
• LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching [59.01894976615714]
  We introduce LVM-Med, the first family of deep networks trained on large-scale medical datasets. We have collected approximately 1.3 million medical images from 55 publicly available datasets. LVM-Med empirically outperforms a number of state-of-the-art supervised, self-supervised, and foundation models.
  arXiv  Detail & Related papers  (2023-06-20T22:21:34Z)
• Align, Reason and Learn: Enhancing Medical Vision-and-Language Pre-training with Knowledge [68.90835997085557]
  We propose a systematic and effective approach to enhance structured medical knowledge from three perspectives. First, we align the representations of the vision encoder and the language encoder through knowledge. Second, we inject knowledge into the multi-modal fusion model to enable the model to perform reasoning using knowledge as the supplementation of the input image and text. Third, we guide the model to put emphasis on the most critical information in images and texts by designing knowledge-induced pretext tasks.
  arXiv  Detail & Related papers  (2022-09-15T08:00:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.