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.
| Comments: | Accepted at CHIL 2026 |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2602.05407 [cs.AI] |
| (or arXiv:2602.05407v3 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2602.05407 arXiv-issued DOI via DataCite |
From: Jun-Min Lee [view email]
[v1]
Thu, 5 Feb 2026 07:44:56 UTC (4,940 KB)
[v2]
Fri, 10 Apr 2026 06:30:00 UTC (4,920 KB)
[v3]
Wed, 15 Apr 2026 05:24:11 UTC (4,918 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。