{"ID":5937085,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-09T13:28:50.14143324Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.05055","arxiv_id":"2607.05055","title":"Toward Trustworthy Large Language Model Agents in Healthcare","abstract":"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.","short_abstract":"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 conversation...","url_abs":"https://arxiv.org/abs/2607.05055","url_pdf":"https://arxiv.org/pdf/2607.05055v1","authors":"[\"Hadi Hasan\",\"Safaa Salman\",\"Adam Tai Abou Dargham\",\"Ammar Mohanna\",\"Ali Chehab\"]","published":"2026-07-06T13:29:07Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"RAG\",\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":613957,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-07T03:14:33.014478982Z","DeletedAt":null,"paper_id":5937085,"paper_url":"https://arxiv.org/abs/2607.05055","paper_title":"Toward Trustworthy Large Language Model Agents in Healthcare","repo_url":"https://github.com/Hadi-Hsn/CareConnect","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}