arXiv cs.MA· Francesca Medda, Hui Gong·· 9 天前AI 评分22
GCAC：面向痴呆症照护的有治理 AI 智能体协调架构与安全契约
Governed AI-Agent Coordination for Dementia Care: Architecture, Safety Contracts, and Evidence-Derived Workflow Verification
AI 导读
论文提出 Governed Closed-loop Agent Coordination（GCAC）架构，让 AI 智能体以受约束方式参与社区痴呆症照护工作流，通过类型化的事件-记忆-决策-行动-结果契约分离观察、四类受治理记忆、规划、确定性策略执行、执行与结果监控。
正文 · 原文
Abstract:Dementia care at home increasingly involves connected sensors, medication devices, electronic records, and assistive technologies. Professionals and family carers must still interpret these observations, reconstruct context, coordinate responses, and verify resolution. Sustaining safe care at home while ensuring timely clinical escalation requires continuity between these tasks. Agentic engineering creates a systems opportunity by combining model interpretation with persistent external memory, planning, authorised tool use, and outcome feedback. This paper presents Governed Closed-loop Agent Coordination (GCAC), an architecture for bounded agent participation in community dementia-care workflows. Evidence on coordination failures and policy obligations is translated into traceable system requirements. GCAC separates observation, four governed memory classes, planning, deterministic policy enforcement, execution, and outcome monitoring through a typed event-memory-decision-action-outcome contract. A worked medication-device example explains how these roles maintain context, allocate responsibility, and distinguish an unrecorded dose from a clinically established omission. A reference harness evaluates 18 evidence-derived traces spanning care gaps, service failure, consent change, stale state, duplicate events, untrusted text, and acute-change routing. GCAC satisfies all 18 contract oracles with zero policy-violating tool calls; event-threshold and stateless-planner controls satisfy 2/18 and 1/18, respectively. Six ablations identify the contribution of memory, policy, and versioning. The results establish architectural conformance. Effects on hospital use, quality of life, staff workload, unpaid care, and net costs require prospective evaluation. GCAC provides a testable basis for accountable coordination that preserves human authority over consequential care decisions.
| Comments: | 16 pages, 2 figures, 6 tables. Includes an executable architecture-verification harness with 18 requirement-derived traces and six component ablations. Expanded contextual framing and discussion; added a worked medication-device example and an Alzheimer's Society AI-agent practice case; updated references. Core architecture and engineering results unchanged |
| Subjects: | Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2609.25956 [cs.MA] |
| (or arXiv:2609.25956v2 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2609.25956 arXiv-issued DOI via DataCite |
Submission history
From: Hui Gong [view email]
[v1]
Tue, 22 Sep 2026 10:09:01 UTC (31 KB)
[v2]
Wed, 7 Oct 2026 18:37:03 UTC (41 KB)
来源：arXiv cs.MA · arxiv.org