用大模型安全自动预约，提升医疗调度效率
Toward Trustworthy Large Language Model Agents in Healthcare
- 结合函数调用与检索增强生成，用多工具协同处理预约流程
- 91.8%任务完成率，每单成本仅0.0324美元，延迟2.2秒
- 严格限制医疗建议，紧急情况即时拦截，适合医疗系统部署
医疗预约调度仍是运营瓶颈，源于人工协调、老旧系统碎片化及高行政成本。本文提出CareConnect，一种以安全为先的对话式医疗物流自动化代理，利用大语言模型（LLM）函数调用、检索增强生成（RAG）和分层确定性安全防护机制。系统协调八类领域专用工具，支持预约、修改、取消及机构信息查询，同时严格限制不提供医疗建议或诊断。关键安全场景通过确定性短路机制实现紧急检测与医疗意图拒绝。我们在包含680个任务导向场景的综合性基准上评估该系统，涵盖端到端流程、多轮交互和边界情况。实验结果表明，任务完成率达91.8%，平均请求延迟2.2秒，安全关键子集合规率达96.0%，单次预约平均运营成本0.0324美元，显著低于人工调度。结果表明，合理限定范围并严格防护的基于LLM的代理可可靠自动化复杂医疗运营流程，兼顾安全性与成本效益。源代码与系统实现已公开于https://github.com/Hadi-Hsn/CareConnect。
原文摘要 · Abstract (English)
Healthcare appointment scheduling remains a persistent operational bottleneck, driven by manual coordination, fragmented legacy systems, and high administrative overhead. These inefficiencies constrain provider availability and degrade patient access to care. This paper presents CareConnect, a safety-first conversational agent for healthcare logistics automation that leverages large language model (LLM) function calling, retrieval-augmented generation (RAG), and layered deterministic safety guardrails. The system orchestrates eight domain-specific tools to support appointment booking, modification, cancellation, and facility information retrieval, while enforcing strict scope constraints that prohibit medical advice or diagnosis. Safety-critical situations are handled through deterministic short-circuit mechanisms for emergency detection and medical intent refusal. We evaluate CareConnect on a comprehensive benchmark of 680 task-oriented scenarios spanning end-to-end workflows, multi-turn interactions, and edge cases. Experimental results demonstrate a 91.8% task completion rate with a median per-request latency of 2.2 seconds, 96.0% safety compliance on the dedicated safety-critical evaluation subset, and an average operational cost of $0.0324 per appointment, yielding a significant cost reduction compared to manual human scheduling. These findings show that carefully scoped and rigorously safeguarded LLM-based agents can reliably automate complex healthcare operational workflows while maintaining safety guarantees and achieving substantial cost efficiency. The source code and system implementation are publicly available at https://github.com/Hadi-Hsn/CareConnect.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。