地球观测（Earth Observation, EO）正从静态预测转向需对数据、工具及地理空间状态进行协同推理的多步骤分析工作流。尽管基础模型与视觉-语言模型已拓展了遥感领域的表征学习与语言驱动的交互能力，且智能体人工智能（agentic AI）已在长时序推理与外部工具调用方面展现出优势，但EO并非通用智能体AI的简单延伸。EO工作流处理的是具有地理参考坐标、多模态且时间结构化的数据；重投影、重采样、合成与聚合等操作会主动改变底层状态，并可能制约后续分析。因此，错误可能在各步骤间隐性传播，而结果的正确性不仅取决于内部逻辑一致性，更依赖于地理空间一致性、时间上有效的比较以及物理合理性。本文指出，这些挑战具有结构性而非偶然性。我们识别出通用智能体模型中常见的隐含假设，分析其在地理空间工作流中失效的原因，并刻画多步骤EO流水线中由此引发的各类失败模式。随后，我们提出面向EO原生智能体的设计原则，聚焦于结构化地理空间状态建模、工具感知型推理、验证器引导的执行机制，以及与地理空间与物理合理性相一致的学习目标。最后，我们梳理若干研究方向，涵盖EO专用基准测试集、监督学习与强化学习的混合范式、约束条件下的自主改进机制，以及超越最终答案准确率的轨迹级评估方法。因此，构建可靠的地理空间智能体，亟需围绕支配EO分析的物理规律、地理空间约束与工作流特性，重新思考智能体的设计范式。

Earth Observation (EO) is moving beyond static prediction toward multi-step analytical workflows that require coordinated reasoning over data, tools, and geospatial state. While foundation models and vision-language models have expanded representation learning and language-grounded interaction for remote sensing, and agentic AI has demonstrated long-horizon reasoning and external tool use, EO is not a straightforward extension of generic agentic AI. EO workflows operate over georeferenced, multi-modal, and temporally structured data, where operations such as reprojection, resampling, compositing, and aggregation actively transform the underlying state and can constrain subsequent analysis. As a result, errors may propagate silently across steps, and correctness depends not only on internal coherence, but also on geospatial consistency, temporally valid comparisons, and physical validity. This position paper argues that these challenges are structural rather than incidental. We identify the implicit assumptions commonly made in generic agentic models, analyze how they break in geospatial workflows, and characterize the resulting failure modes in multi-step EO pipelines. We then outline design principles for EO-native agents centered on structured geospatial state, tool-aware reasoning, verifier-guided execution, and learning objectives aligned with geospatial and physical validity. Finally, we present research directions spanning EO-specific benchmarks, hybrid supervised and reinforcement learning, constrained self-improvement, and trajectory-level evaluation beyond final-answer accuracy. Building reliable geospatial agents therefore requires rethinking agent design around the physical, geospatial, and workflow constraints that govern EO analysis.