Geospatial reasoning is essential for real-world applications such as urban analytics, transportation planning, and disaster response. However, existing LLM-based agents often fail at genuine geospatial computation, relying instead on web search or pattern matching while hallucinating spatial relationships. We present Spatial-Agent, an AI agent grounded in foundational theories of spatial information science. Our approach formalizes geo-analytical question answering as a concept transformation problem, where natural-language questions are parsed into executable workflows represented as GeoFlow Graphs -- directed acyclic graphs with nodes corresponding to spatial concepts and edges representing transformations. Drawing on spatial information theory, Spatial-Agent extracts spatial concepts, assigns functional roles with principled ordering constraints, and composes transformation sequences through template-based generation. Extensive experiments on MapEval-API and MapQA benchmarks demonstrate that Spatial-Agent significantly outperforms existing baselines including ReAct and Reflexion, while producing interpretable and executable geospatial workflows.

翻译：地理空间推理对于城市分析、交通规划和灾害响应等现实应用至关重要。然而，现有基于大语言模型的智能体往往无法进行真正的地理空间计算，而是依赖网络搜索或模式匹配，同时产生空间关系幻觉。本文提出空间智能体，这是一个基于空间信息科学基础理论的AI智能体。我们的方法将地理分析问答形式化为概念转换问题，其中自然语言问题被解析为可执行的工作流，表示为地理流图——一种有向无环图，其节点对应空间概念，边表示转换关系。借鉴空间信息理论，空间智能体提取空间概念，通过原则性排序约束分配功能角色，并通过基于模板的生成组合转换序列。在MapEval-API和MapQA基准测试上的大量实验表明，空间智能体显著优于包括ReAct和Reflexion在内的现有基线方法，同时生成可解释且可执行的地理空间工作流。