CodeClinic：评估临床推理代理的编码技能自动化
CodeClinic: Evaluating Automation of Coding Skills for Clinical Reasoning Agents
AI总结：
CodeClinic通过MIMIC-IV构建基准，评估LLM代理是否能合成和组合可重用的临床技能，而非依赖固定工具库，包含纵向ICU监控和组合信息检索任务，提升多步推理效率。
摘要：
基于大语言模型（LLMs）的临床推理代理旨在自动化重症监护室（ICU）监测和患者状态跟踪等任务。现有系统通常依赖手动编写的临床工具或技能，但维护这些工具库需要大量专家努力，而零样本查询或代码生成往往产生低效且不可靠的推理链，尤其在机构特定的临床政策下。我们引入CodeClinic基准，基于MIMIC-IV评估LLM代理是否能合成和组合可重用的临床技能而非依赖固定工具箱。该基准包含两个互补任务：纵向ICU监控和组合信息检索。纵向设置模拟每四小时进行结构化决策的患者轨迹监控，涉及25种发现和8种临床家族；组合设置涵盖63k实例，跨越259个任务和9个领域，并按组合依赖深度分层以评估日益复杂的多步推理。我们进一步提出一个离线自动形式化流程，通过迭代LLM优化将自然语言临床指南转换为可重用和验证的Python技能库。与零样本代码生成相比，所生成的库提高了一致性，同时减少了每查询的token使用量高达40%。
英文摘要：
Clinical reasoning agents based on large language models (LLMs) aim to automate tasks such as intensive care unit (ICU) monitoring and patient state tracking from electronic health records (EHRs). Existing systems typically rely on manually curated clinical tools or skills for concepts such as sepsis detection and organ failure assessment. However, maintaining these tool libraries requires substantial expert effort, while zero-shot querying or code generation often produces inefficient and unreliable reasoning chains, especially under institution-specific clinical policies. We introduce CodeClinic, a benchmark built on MIMIC-IV for evaluating whether LLM agents can synthesize and compose reusable clinical skills instead of relying on fixed toolboxes. The benchmark contains two complementary tasks: longitudinal ICU surveillance and compositional information seeking. The longitudinal setting simulates monitoring patient trajectories with structured decisions every four hours across 25 findings and eight clinical families, while the compositional setting spans 63k instances across 259 tasks in nine domains and is stratified by compositional dependency depth to evaluate increasingly complex multi-step reasoning. We further propose an offline autoformalization pipeline that converts natural-language clinical guidelines into reusable and verified Python skill libraries through iterative LLM refinement. Compared with zero-shot code generation, the resulting libraries improve consistency while reducing per-query token usage by up to 40%.
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。
