arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.06902cs.AI
收藏

通过增强状态的逻辑技能赋能本地可部署的医疗代理以用于基于FHIR的临床任务

Empowering Locally Deployable Medical Agent via State Enhanced Logical Skills for FHIR-based Clinical Tasks

Department of Computer Science, University of Liverpool(利物浦大学计算机科学系);The Hong Kong Polytechnic University(香港理工大学);Beijing Normal University(北京师范大学);School of Computing, University of Georgia(佐治亚大学计算机学院);Department of Eye and Vision, University of Liverpool(利物浦大学眼科学与视觉系)

Wanrong Yang, Zhengliang Liu, Yuan Li, Bingjie Yan, Lingfang Li, Mingguang He, Dominik Wojtczak, Yalin Zheng, Danli Shi

AI总结:

本文提出SELSM框架,通过增强状态的逻辑技能提升本地医疗代理在FHIR临床任务中的零样本能力,实现100%任务完成率和22.67%的成功率提升。

摘要:

尽管大语言模型显示出作为主动医疗代理的巨大潜力,但其在现实中的部署受到隐私约束下数据稀缺的严重限制。为克服这一问题,我们提出了一种训练自由的框架,即状态增强的逻辑技能记忆(SELSM),该框架将模拟的临床轨迹提炼为实体无关的操作规则,存在于抽象技能空间中。在推理过程中,查询锚定的两阶段检索机制动态获取这些实体无关的逻辑先验,以引导代理的逐步推理,从而有效解决状态多义性问题。在MedAgentBench上进行评估——这是唯一经过真实临床数据验证的高保真虚拟EHR沙盒基准——SELSM显著提升了本地可部署基础模型(30B-32B参数)的零样本能力。值得注意的是,在Qwen3-30B-A3B主干上,我们的框架完全消除了任务链中断,实现了100%的完成率,将整体成功率提高了22.67个百分点,显著优于现有记忆增强基线。本研究证明,为模型配备一个动态更新、状态增强的认知支架,是隐私保护且计算高效地使AI代理适应临床信息系统的一种路径。尽管目前仅在基于FHIR的EHR交互上得到验证,但SELSM的实体无关设计为更广泛的临床部署提供了原则性的基础。

英文摘要:

While Large Language Models demonstrate immense potential as proactive Medical Agents, their real-world deployment is severely bottlenecked by data scarcity under privacy constraints. To overcome this, we propose State-Enhanced Logical-Skill Memory (SELSM), a training-free framework that distills simulated clinical trajectories into entity-agnostic operational rules within an abstract skill space. During inference, a Query-Anchored Two-Stage Retrieval mechanism dynamically fetches these entity-agnostic logical priors to guide the agent's step-by-step reasoning, effectively resolving the state polysemy problem. Evaluated on MedAgentBench -- the only authoritative high-fidelity virtual EHR sandbox benchmarked with real clinical data -- SELSM substantially elevates the zero-shot capabilities of locally deployable foundation models (30B--32B parameters). Notably, on the Qwen3-30B-A3B backbone, our framework completely eliminates task chain breakdowns to achieve a 100\% completion rate, boosting the overall success rate by an absolute 22.67\% and significantly outperforming existing memory-augmented baselines. This study demonstrates that equipping models with a dynamically updatable, state-enhanced cognitive scaffold is a privacy-preserving and computationally efficient pathway for local adaptation of AI agents to clinical information systems. While currently validated on FHIR-based EHR interactions as an initial step, the entity-agnostic design of SELSM provides a principled foundation toward broader clinical deployment.

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。

↑