The paradigm of Earth Observation analysis is shifting from static deep learning models to autonomous agentic AI. Although recent vision foundation models and multimodal large language models advance representation learning, they often lack the sequential planning and active tool orchestration required for complex geospatial workflows. This survey presents the first comprehensive review of agentic AI in remote sensing. We introduce a unified taxonomy distinguishing between single-agent copilots and multi-agent systems while analyzing architectural foundations such as planning mechanisms, retrieval-augmented generation, and memory structures. Furthermore, we review emerging benchmarks that move the evaluation from pixel-level accuracy to trajectory-aware reasoning correctness. By critically examining limitations in grounding, safety, and orchestration, this work outlines a strategic roadmap for the development of robust, autonomous geospatial intelligence.

翻译：地球观测分析范式正从静态深度学习模型转向自主智能体人工智能。尽管近期视觉基础模型和多模态大语言模型推动了表征学习的发展，它们往往缺乏复杂地理空间工作流所需的序列化规划与主动工具编排能力。本综述首次系统回顾遥感领域的智能体人工智能研究。我们提出了统一分类体系，区分单智能体协同系统与多智能体系统，同时分析了规划机制、检索增强生成和记忆结构等架构基础。此外，我们综述了将评估标准从像素级精度转向轨迹感知推理正确性的新兴基准测试。通过批判性审视其在语义基础、安全性和系统编排方面的局限，本研究为开发鲁棒自主的地理空间智能系统绘制了战略路线图。