Spatial-Agent: Agentic Geo-spatial Reasoning with Scientific Core Concepts
This addresses the problem of inaccurate geospatial reasoning for applications such as urban analytics and disaster response, representing a novel method for a known bottleneck.
The paper tackled the problem of LLM-based agents failing at genuine geospatial computation by introducing Spatial-Agent, which formalizes geo-analytical question answering as a concept transformation problem using GeoFlow Graphs. The result was that Spatial-Agent significantly outperformed existing baselines like ReAct and Reflexion on MapEval-API and MapQA benchmarks.
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.