arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.20176cs.CL
收藏

ClinSeekAgent: 自动化多模态证据检索以实现代理临床推理

ClinSeekAgent: Automating Multimodal Evidence Seeking for Agentic Clinical Reasoning

UC Santa Cruz(加州大学圣克ruz分校)

Juncheng Wu, Letian Zhang, Yuhan Wang, Haoqin Tu, Hardy Chen, Zijun Wang, Cihang Xie, Yufan He, Can Zhao, Daguang Xu, Yucheng Tang, Yuyin Zhou

AI总结:

本文提出ClinSeekAgent,一种自动化代理框架,用于动态多模态证据检索,旨在从异构来源主动检索、迭代规划和综合多模态证据,从而提升临床决策支持。

摘要:

大型语言模型(LLMs)和代理系统在临床决策支持中展现出潜力,但现有研究大多假设证据已预先整理并提供给模型。现实中的临床工作流程要求代理主动检索、迭代规划和综合来自异质来源的多模态证据。在本文中,我们介绍了ClinSeekAgent,一种自动化代理框架,用于动态多模态证据检索,将范式从被动证据消费转向主动证据获取。仅给定一个临床查询和对原始数据源的访问权限,ClinSeekAgent通过查询医学知识库、导航原始电子健康记录(EHR)和调用医学影像工具来收集证据;随着新信息的出现,它会细化假设;并将收集到的证据整合到基于事实的临床决策中。ClinSeekAgent既作为推理时间的代理用于前沿LLMs,也作为训练时间的流水线,用于将高质量的代理轨迹提炼成紧凑的开源模型。为了验证其推理时间的有效性,我们构建了ClinSeek-Bench,它将固定预选证据的Curated Input推理与原始临床数据上的自动化证据检索相结合。在仅文本EHR任务中,ClinSeekAgent将Claude Opus 4.6的总体F1从60.0提升到63.2,将MiniMax M2.5从43.1提升到47.3,并在9个评估的主机模型中有7个显示出积极的风险预测增益。在多模态任务中,ClinSeekAgent将Claude Opus 4.6的分数从47.5提升到62.6(+15.1);所有评估的模型在三个与CXR相关的任务组中均有所提升。我们进一步通过将代理证据检索轨迹提炼成ClinSeek-35B-A3B来验证ClinSeekAgent作为训练流水线的有效性,该模型在现有AgentEHR-Bench上实现了34.0的平均F1,比其Qwen3.5-35B-A3B基线提高了+11.9点,并接近Claude Opus 4.6。

英文摘要:

Large language models (LLMs) and agentic systems have shown promise for clinical decision support, but existing works largely assume that evidence has already been curated and handed to the model. Real-world clinical workflows instead require agents to actively seek, iteratively plan, and synthesize multimodal evidence from heterogeneous sources. In this paper, we introduce ClinSeekAgent, an automated agentic framework for dynamic multimodal evidence seeking that shifts the paradigm from passive evidence consumption to active evidence acquisition. Given a clinical task and access to raw patient data, ClinSeekAgent queries longitudinal EHR records and invokes imaging analysis tools when relevant; refines its hypotheses as new information emerges; and integrates the collected evidence into grounded clinical decisions. We validate ClinSeekAgent in two roles: as an inference-time agent for frontier LLMs and as a training pipeline for open-source models. For inference-time validation, we construct ClinSeek-Bench, which covers 13 text-only EHR task categories and 6 multimodal EHR--chest X-ray task categories, and pairs each question with both a Curated Input of pre-selected evidence and the raw patient data for automated evidence seeking. Without any benchmark-specific curation, ClinSeekAgent significantly outperforms curated input for both Claude Opus 5 and GPT-5.6 Sol, improving overall F1 from 66.5 to 68.8 and from 60.0 to 62.5 on multimodal tasks. The ablations show that the performance gain come from multi-round evidence seeking rather than from access to more of the patient record. For training-time validation, we fine-tune Qwen3.5-35B-A3B on ClinSeekAgent trajectories generated by GPT-5.6 Sol. The resulting ClinSeek-35B-A3B reaches 35.6 average F1 on AgentEHR-Bench, outperforming all evaluated open-source models, including ones more than ten times larger, as well as Claude Opus 5.

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。

↑