通过经验驱动的自我技能发现进化医疗影像代理
Evolving Medical Imaging Agents via Experience-driven Self-skill Discovery
AI总结：
MACRO通过经验驱动的自我技能发现，实现医疗影像代理的自我进化，提升多步骤协调精度和跨领域泛化能力。
摘要：
临床影像解读本质上是多步骤且以工具为中心的：临床医生反复结合视觉证据与患者背景，量化发现并通过一系列专门的程序细化其决策。尽管基于大语言模型的代理有潜力协调此类异构医学工具，但现有系统在部署后将工具集和调用策略视为静态。这种设计在现实世界领域变化、跨任务和不断演变的诊断需求下容易崩溃，其中预定义的工具链经常退化并需要昂贵的人工重新设计。我们提出了MACRO，一个自我进化、经验增强的医疗代理，从静态工具组合转向经验驱动的工具发现。从已验证的执行轨迹中，代理自动识别反复有效的多步骤工具序列，将其综合为可重用的复合工具，并将其注册为新的高级原始工具，这些工具不断扩展其行为库。一个轻量级的图像特征记忆为工具选择提供了视觉-临床背景，而GRPO-like训练循环强化了发现复合工具的可靠调用，使代理能够通过最小的监督实现闭环自我改进。在多样化的医学影像数据集和任务上的广泛实验表明，自主复合工具发现一致地提高了多步骤协调精度和跨领域泛化能力，优于强大的基线和最近最先进的代理方法，弥合了静态工具使用与适应性、情境感知临床AI辅助之间的差距。代码将在接受后提供。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
