CAREAgent能生成精准可执行的临床医嘱，提升医疗决策落地效率。
CAREAgent: Clinical Agent with Structured Reasoning and Tool-Integrated for Order Generation
- 构建分两阶段的智能体推理数据，模拟真实临床工具使用流程
- 在未见过的ClinicalBench上F1得分提升超5%，优于现有方法
- 适合医疗AI研发者与临床决策系统开发者参考
临床医嘱生成是连接临床决策与实际操作的关键环节，将医疗判断转化为具体可执行的指令。现有智能体多聚焦粗粒度决策，忽略医嘱所需的细粒度、可执行信息。为此，我们提出CAREAgent，一种面向临床医嘱生成的智能体。为支持训练，我们设计了两阶段的智能体推理数据构建方法：首先构建与真实临床工具使用一致的可验证推理轨迹；其次通过格式合规性、医嘱有效性及临床合理性三重过滤。基于构建数据，模型先通过监督微调学习基础推理模式与医学知识，再经多维度奖励函数的强化学习优化复杂临床推理能力。多个基准测试表明CAREAgent有效：在未参与训练的ClinicalBench上，其F1分数分别比单智能体、多智能体及基于推理的现有方法提升5.05%、2.09%和0.86%。
原文摘要 · Abstract (English)
Clinical order generation serves as a critical bridge between clinical decision-making and real-world practice, translating medical decisions into concrete and executable orders. Existing agents mainly focus on coarse-grained decisions and overlook the fine-grained, executable information required for clinical orders. To address this gap, we propose CAREAgent, an agent for clinical order generation. To support its training, we introduce a two-stage agentic reasoning data construction method. First, we design an agent framework that constructs verifiable reasoning trajectories aligned with realistic clinical tool usage. Second, we filter reasoning trajectories by format compliance, order validity, and clinical plausibility. Building on the constructed data, the model is first trained via supervised fine-tuning to acquire fundamental reasoning formats and medical knowledge, and is subsequently optimized through reinforcement learning with multi-dimensional reward functions to enhance complex clinical reasoning capabilities. Experiments on multiple benchmarks demonstrate the effectiveness of CAREAgent. On ClinicalBench (unseen during training), CAREAgent improves the F1 score by 5.05%, 2.09%, and 0.86% over the single-agent, multi-agent, and agentic reasoning methods, respectively.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。