H-AdminSim: A Multi-Agent Simulator for Realistic Hospital Administrative Workflows with FHIR Integration
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Scheduling | H-AdminSim Primary Level 1.0 | -- | 6 | |
| Scheduling | H-AdminSim Secondary Level 1.0 | -- | 6 | |
| Scheduling | H-AdminSim Tertiary Level 1.0 | -- | 6 | |
| Department assignment | H-AdminSim Primary hospital level 1.0 | -- | 3 | |
| Department assignment | H-AdminSim Secondary hospital level 1.0 | -- | 3 | |
| Department assignment | H-AdminSim Tertiary hospital level 1.0 | -- | 3 | |
| Intake | H-AdminSim Primary Level 1.0 | -- | 3 | |
| Intake | H-AdminSim Secondary Level 1.0 | -- | 3 | |
| Intake | H-AdminSim Tertiary Level 1.0 | -- | 3 | |
| Intake-task dialogue assessment | H-AdminSim Intake-Task (Human Evaluation) | -- | 3 |