Spatial-Agent: Agentic Geo-spatial Reasoning with Scientific Core Concepts

TL;DR

Spatial-Agent introduces a novel geo-spatial reasoning framework grounded in spatial information science, transforming natural language questions into executable workflows for improved accuracy in geospatial tasks.

Contribution

It formalizes geo-analytical question answering as a concept transformation problem using GeoFlow Graphs, integrating spatial theories into AI reasoning.

Findings

Outperforms existing baselines like ReAct and Reflexion

Produces interpretable geospatial workflows

Demonstrates significant accuracy improvements on benchmarks

Abstract

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.