H-AdminSim: A Multi-Agent Simulator for Realistic Hospital Administrative Workflows with FHIR Integration
cs.AI, cs.CL
Submitted: 2026-02-05
Updated: 2026-04-15
Comments: Accepted at CHIL 2026
Journal ref: Proceedings of the Conference on Health, Inference, and Learning (CHIL), PMLR 333:572-613, 2026
Project page: https://ljm565.github.io/h_adminsim_project
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
The gist: 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.
Terminology
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 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.
Sources
- Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactions
- The Llama 3 Herd of Models
- MedSimAI: Simulation and Formative Feedback Generation to Enhance Deliberate Practice in Medical Education
- PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions
- Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents
- Automatic Interactive Evaluation for Large Language Models with State Aware Patient Simulator
- MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agents
- ClinicalLab: Aligning Agents for Multi-Departmental Clinical Diagnostics in the Real World
- Qwen3 Technical Report
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems