cs.CVNov 19, 2026

Harnessing Medical Visual-Language Models with Agentic Evidence Management

Authors: Qiming Huang, Hanze Dong, Jipeng Zhang, Mike Zheng Shou, Xinxing Xu, Furu Wei

Organizations: National University of Singapore · Microsoft

Abstract

Medical vision-language agents increasingly rely on segmentation tools, and recent work has focused on acquiring the right mask, often treating a good mask as the end point of tool use. But do these agents use the resulting evidence effectively? To answer this question, we need a benchmark that separates evidence use from segmentation quality, spans multiple medical image types, and allows the same mask to be presented in different ways. Existing medical VQA datasets do not jointly provide these properties. We therefore construct Mask-Evidence MedVQA, a 2.5K-example benchmark spanning four image types, where each question is paired with an answer-relevant ground-truth mask and multiple possible renderings. Our study reveals two limitations of direct tool use. First, evidence presentation matters. Different renderings of the same fixed mask can substantially change model behavior. Second, masks introduce an evidence trade-off. Highlighting a relevant region can expose diagnostic evidence the model previously missed, but the added visual cue can also induce incorrect associations. As a result, even a ground-truth mask can correct some answers while turning initially correct ones into incorrect ones. Together, these findings show that acquiring the right mask is not enough. An agent must also decide how to present the evidence and whether it should change the answer. We therefore introduce TUNE (Tool Use is Not Enough), an evidence-management harness that explicitly manages what evidence to acquire, how to present it, and whether to accept the resulting answer update. Across three public medical VQA benchmarks, evidence management improves the fine-tuned Qwen3.5-9B backbone's mean accuracy by 4.0 percentage points. Full TUNE improves over direct tool use by 9.1 points on average across seven benchmarks and achieves competitive results against existing medical VLMs and agents.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. MedLVR: Latent Visual Reasoning for Reliable Medical Visual Question Answering

    Apr 10, 2026Suyang Xi, Songtao Hu, Yuxiang Lai +4Medical Visual Question AnsweringMedical VLMs

  2. Visual Harness Scales General VLMs to Medical Images

    Nov 17, 2026Shaowen Wan, Hanqi Jiang, Zihao Wu +6Medical VLMsTool Use in VLMs

  3. MedOpenClaw and MedFlowBench: Auditing Medical Agents in Full-Study Workflows

    Mar 25, 2026Weixiang Shen, Chengzhi Shen, Yanzhu Hu +12Medical VLMsMedical Image Benchmarks