受治理的AI智能体协调用于痴呆症护理：架构、安全契约与基于证据的工作流验证
Governed AI-Agent Coordination for Dementia Care: Architecture, Safety Contracts, and Evidence-Derived Workflow Verification
浏览论文内容
中文总结 AI 辅助
本文提出受治理的闭环智能体协调架构GCAC，通过类型化契约分离记忆、策略与执行，在18条痴呆症护理证据轨迹上实现零违规，验证了智能体系统在保留人类权威下的自动化协调能力。
中文摘要 AI 辅助
痴呆症护理日益涉及连接的传感器、药物设备、电子记录和辅助技术。互操作性可以传输观察结果，但无法维持可问责的护理状态、协调证据、确定谁可以行动或验证解决方案。从大型语言模型向智能体工程的转变创造了一个系统机会：外部运行时可以在多个事件之间维持记忆，基于目标和约束进行规划，调用工具，观察结果，并执行治理。本文提出了受治理的闭环智能体协调（GCAC），一种用于社区痴呆症护理工作流中受限智能体参与的架构。关于护理协调失败和政策义务的证据被转化为可追踪的系统需求。GCAC通过类型化的事件-记忆-决策-行动-结果契约分离观察、受治理的记忆、规划、确定性策略执行、执行和结果监控。一个参考测试平台评估了18条基于证据的轨迹，涵盖缺失记录、药物冲突、照护者报告、服务失败、同意变更、过期状态、重复事件、不可信文本和疑似急性神经变化。GCAC满足所有18个契约预言机，零次违反策略的工具调用，并正确保留义务、拒绝过期状态、创建人工交接并记录工作流闭合。事件阈值和无状态规划器控制分别满足2/18和1/18的预言机。组件消融将失败定位到被移除的记忆、策略或版本控制功能。结果确立了架构符合性而非临床有效性，并展示了智能体系统如何自动化协调、路由、文档记录和随访，同时保留人类对重大护理决策的权威。
英文摘要
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.
发表机构
- UCL Institute of Finance and Technology（伦敦大学学院金融与技术研究所）
- University College London（伦敦大学学院）
机构由 AI 辅助整理，请以论文原文为准。
