H-AdminSim: A Multi-Agent Simulator for Realistic Hospital Administrative Workflows with FHIR Integration

2026-02-05

AI Summary

Existing research is often confined to physician–patient interactions or isolated administrative subtasks, failing to replicate the complex administrative workflows of real-world hospitals. This work proposes the first end-to-end multi-agent simulation framework that integrates realistic workflow modeling with the FHIR healthcare data standard, enabling a high-fidelity, scalable, and interoperable environment for simulating hospital administrative automation across institutions. The framework supports fine-grained, systematic evaluation of large language models (LLMs) under realistic loads—up to tens of thousands of daily requests—and establishes the first standardized benchmark for assessing LLM performance in administrative automation tasks within healthcare settings.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

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.

Problem

• hospital administrative workflows
• LLM-based automation
• multi-agent simulation
• FHIR integration
• realistic workflow complexity

Innovation

• multi-agent simulation
• FHIR integration
• hospital administrative workflows
• LLM evaluation
• realistic data generation