ANASSA：面向空间智能的智能体AI编排框架
ANASSA: An Agentic AI Orchestration Framework for Spatial Intelligence
- Research Scientist（研究科学家）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对现有智能体GIS系统在推理、执行与评估上的碎片化问题，提出ANASSA编排框架，通过四层十一组件及六步认知循环实现可追溯、可复现、可问责的空间工作流。
AI中文摘要：
大型语言模型（LLM）和大型多模态模型（LMM）的出现催生了一类新型智能体系统，能够将自然语言理解与基于工具的执行相结合。在地理信息系统（GIS）领域，这一转变正在将传统的、专家驱动的工作流程转变为半自主系统，这些系统能够解释用户意图、构建空间工作流程并执行地理空间分析任务。然而，现有方法仍受限于推理、执行和评估的碎片化整合，尤其是在复杂的现实环境中。本研究综合了智能体GIS框架、基准和综述方面的最新进展，以识别空间推理、执行鲁棒性、验证、治理和评估方面的局限性。基于这些见解，本文提出了ANASSA（自主神经智能体空间系统架构），这是一个智能体AI编排框架，在统一系统设计中整合了结构化空间推理、多智能体工作流编排、执行反馈、权威空间验证、来源追踪、不确定性处理以及人类决策权。其贡献在于架构层面的规范：跨四个层的十一个组件、六步地理空间AI认知循环、跨组件契约以及治理机制，旨在使智能体地理空间工作流可追溯、可复现且可问责。实证性能评估留待实施和部署研究中进行。
英文摘要：
The emergence of large language models (LLMs) and large multimodal models (LMMs) has enabled a new class of agentic systems capable of integrating natural language understanding with tool-based execution. In geographic information systems (GIS), this shift is transforming traditional, expert-driven workflows into semiautonomous systems that can interpret user intent, construct spatial workflows, and execute geospatial analysis tasks. However, existing approaches remain limited by fragmented integration of reasoning, execution, and evaluation, particularly in complex, real-world environments. This study synthesizes recent advances in agentic GIS frameworks, benchmarks, and surveys to identify limitations in spatial reasoning, execution robustness, validation, governance, and evaluation. Building on these insights, it introduces ANASSA (Autonomous Neural Agents for Spatial Systems Architecture), an agentic AI orchestration framework that integrates structured spatial reasoning, multi-agent workflow orchestration, execution feedback, authoritative spatial validation, provenance, uncertainty handling, and human decision authority within a unified system design. The contribution is an architecture-level specification: eleven components across four layers, a six-step Geospatial AI Cognitive Loop, cross-component contracts, and governance mechanisms intended to make agentic geospatial workflows traceable, reproducible, and accountable. Empirical performance evaluation is reserved for implementation and deployment studies.
