H-AdminSim: A Multi-Agent Simulator for Realistic Hospital Administrative Workflows with FHIR Integration
This provides a standardized testbed for LLM-driven administrative automation in hospitals, addressing a domain-specific gap in healthcare simulation.
The authors tackled the lack of realistic simulation environments for hospital administrative workflows by developing H-AdminSim, a multi-agent simulator with FHIR integration that processes over 10,000 daily requests and enables systematic LLM evaluation through quantitative rubrics.
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 end-to-end 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.