构建可模拟万级医院行政任务的多智能体仿真系统
H-AdminSim: A Multi-Agent Simulator for Realistic Hospital Administrative Workflows with FHIR Integration
- 用多智能体模拟真实医院行政流程，支持复杂协作
- 集成FHIR标准，实现跨系统数据互通与统一测试
- 专为评估大模型在行政自动化中的表现设计
医院行政部门处理大量日常事务，大型医院每日需处理超过10,000项请求，推动了基于大语言模型（LLM）的自动化研究。然而，以往工作主要聚焦于患者-医生交互或孤立的行政子任务，未能捕捉真实行政流程的复杂性。为此，我们提出H-AdminSim，一个结合真实数据生成与多智能体仿真机制的综合性仿真框架，用于模拟医院行政工作流。通过详细的评分体系对各项任务进行量化评估，实现对不同大模型的系统性比较。借助FHIR集成，H-AdminSim提供了一个统一且可互操作的环境，支持在异构医院场景下测试行政工作流，成为评估大模型驱动行政自动化的标准化测试平台。
原文摘要 · Abstract (English)
Hospital administration departments handle a wide range of operational tasks and, in large hospitals, process over 10,000 requests per day, driving growing interest in LLM-based automation. However, prior work has focused primarily on patient-physician interactions or isolated administrative subtasks, failing to capture the complexity of real administrative workflows. To address this gap, we propose H-AdminSim, a comprehensive simulation framework that combines realistic data generation with multi-agent-based simulation of hospital administrative workflows. These tasks are quantitatively evaluated using detailed rubrics, enabling systematic comparison of LLMs. Through FHIR integration, H-AdminSim provides a unified and interoperable environment for testing administrative workflows across heterogeneous hospital settings, serving as a standardized testbed for assessing the feasibility and performance of LLM-driven administrative automation.
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。