Research

Paper

AI LLM March 06, 2026

Evolving Medical Imaging Agents via Experience-driven Self-skill Discovery

Authors

Lin Fan, Pengyu Dai, Zhipeng Deng, Haolin Wang, Xun Gong, Yefeng Zheng, Yafei Ou

Abstract

Clinical image interpretation is inherently multi-step and tool-centric: clinicians iteratively combine visual evidence with patient context, quantify findings, and refine their decisions through a sequence of specialized procedures. While LLM-based agents promise to orchestrate such heterogeneous medical tools, existing systems treat tool sets and invocation strategies as static after deployment. This design is brittle under real-world domain shifts, across tasks, and evolving diagnostic requirements, where predefined tool chains frequently degrade and demand costly manual re-design. We propose MACRO, a self-evolving, experience-augmented medical agent that shifts from static tool composition to experience-driven tool discovery. From verified execution trajectories, the agent autonomously identifies recurring effective multi-step tool sequences, synthesizes them into reusable composite tools, and registers these as new high-level primitives that continuously expand its behavioral repertoire. A lightweight image-feature memory grounds tool selection in a visual-clinical context, while a GRPO-like training loop reinforces reliable invocation of discovered composites, enabling closed-loop self-improvement with minimal supervision. Extensive experiments across diverse medical imaging datasets and tasks demonstrate that autonomous composite tool discovery consistently improves multi-step orchestration accuracy and cross-domain generalization over strong baselines and recent state-of-the-art agentic methods, bridging the gap between brittle static tool use and adaptive, context-aware clinical AI assistance. Code will be available upon acceptance.

Metadata

arXiv ID: 2603.05860
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-03-06
Fetched: 2026-03-09 06:05

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.05860v1</id>\n    <title>Evolving Medical Imaging Agents via Experience-driven Self-skill Discovery</title>\n    <updated>2026-03-06T03:34:47Z</updated>\n    <link href='https://arxiv.org/abs/2603.05860v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.05860v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Clinical image interpretation is inherently multi-step and tool-centric: clinicians iteratively combine visual evidence with patient context, quantify findings, and refine their decisions through a sequence of specialized procedures. While LLM-based agents promise to orchestrate such heterogeneous medical tools, existing systems treat tool sets and invocation strategies as static after deployment. This design is brittle under real-world domain shifts, across tasks, and evolving diagnostic requirements, where predefined tool chains frequently degrade and demand costly manual re-design. We propose MACRO, a self-evolving, experience-augmented medical agent that shifts from static tool composition to experience-driven tool discovery. From verified execution trajectories, the agent autonomously identifies recurring effective multi-step tool sequences, synthesizes them into reusable composite tools, and registers these as new high-level primitives that continuously expand its behavioral repertoire. A lightweight image-feature memory grounds tool selection in a visual-clinical context, while a GRPO-like training loop reinforces reliable invocation of discovered composites, enabling closed-loop self-improvement with minimal supervision. Extensive experiments across diverse medical imaging datasets and tasks demonstrate that autonomous composite tool discovery consistently improves multi-step orchestration accuracy and cross-domain generalization over strong baselines and recent state-of-the-art agentic methods, bridging the gap between brittle static tool use and adaptive, context-aware clinical AI assistance. Code will be available upon acceptance.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-03-06T03:34:47Z</published>\n    <arxiv:comment>18 pages, 4 figures, 3 tables</arxiv:comment>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Lin Fan</name>\n    </author>\n    <author>\n      <name>Pengyu Dai</name>\n    </author>\n    <author>\n      <name>Zhipeng Deng</name>\n    </author>\n    <author>\n      <name>Haolin Wang</name>\n    </author>\n    <author>\n      <name>Xun Gong</name>\n    </author>\n    <author>\n      <name>Yefeng Zheng</name>\n    </author>\n    <author>\n      <name>Yafei Ou</name>\n    </author>\n  </entry>"
}