Evolving Medical Imaging Agents via Experience-driven Self-skill Discovery
This addresses the need for adaptive, context-aware clinical AI assistance in medical imaging, offering a novel approach to overcome domain shifts and evolving diagnostic requirements, though it is incremental in building on existing agentic methods.
The paper tackled the problem of brittle static tool use in LLM-based medical imaging agents by proposing MACRO, a self-evolving agent that autonomously discovers and synthesizes effective multi-step tool sequences, resulting in improved multi-step orchestration accuracy and cross-domain generalization over strong baselines and state-of-the-art methods.
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.