摘要：处理地理空间数据的 Agentic AI 系统需要的不仅是自主推理和工具使用；它们还必须支持显式编排、空间验证、治理、溯源、故障处理以及人类决策权威。先前工作提出了 ANASSA——一个用于空间智能的 Agentic AI 编排框架，确立了受治理 Agent 执行的高层组件和职责边界（arXiv:2609.14824）。然而，该框架并未说明应如何将这些高层职责系统化地分解为面向实现的低层架构。本文通过应用设计科学研究（DSR）弥补这一缺口，将 ANASSA 框架从高层架构（HLA）职责细化为低层架构（LLA）。最终设计在保留基础框架职责边界的同时，将其转化为可执行的架构结构，包括 47 个逻辑角色、版本化任务图、基于能力的 Agent 选择、类型化契约、显式运行时状态、空间验证机制、治理控制、故障与恢复路径以及溯源记录。该架构通过端到端执行轨迹进行展示，并针对需求可追溯性、内部一致性、职责保留和技术独立性进行分析评估。最终形成的从高层到低层设计，在 ANASSA 框架与未来系统实现之间提供了一座面向实现的桥梁，定义了如何在不将架构绑定到特定 AI 模型、地理空间平台、通信协议或部署环境的前提下，使受治理的空间 Agent 工作流具备可检查、可重建和可测试的特性。

Abstract:Agentic AI systems operating over geospatial data require more than autonomous reasoning and tool use; they must also support explicit orchestration, spatial validation, governance, provenance, failure handling, and human decision authority. Prior work introduced ANASSA, an agentic AI orchestration framework for spatial intelligence that established high-level components and responsibility boundaries for governed agentic execution (arXiv:2609.14824). However, the framework did not specify how those high-level responsibilities should be systematically decomposed into an implementation-facing low-level architecture. This paper addresses that gap by applying Design Science Research (DSR) to refine the ANASSA framework from high-level architectural (HLA) responsibilities into a low-level architecture (LLA). The resulting design preserves the responsibility boundaries of the foundational framework while translating them into executable architectural structures, including 47 logical roles, versioned task graphs, capability-based agent selection, typed contracts, explicit runtime states, spatial validation mechanisms, governance controls, failure and recovery paths, and provenance records. The architecture is demonstrated through an end-to-end execution trace and analytically evaluated for requirements traceability, internal consistency, responsibility preservation, and technology independence. The resulting high-level-to-low-level design provides an implementation-facing bridge between the ANASSA framework and future system implementations, defining how governed spatial agentic workflows can be made inspectable, reconstructable, and testable without binding the architecture to a specific AI model, geospatial platform, communication protocol, or deployment environment.