Guardado en:
Detalles Bibliográficos
Autores principales: Bao, Riyang, Yang, Cheng, Yu, Dazhou, Tang, Zhexiang, Mai, Gengchen, Zhao, Liang
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2601.16965
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917219724689408
author Bao, Riyang
Yang, Cheng
Yu, Dazhou
Tang, Zhexiang
Mai, Gengchen
Zhao, Liang
author_facet Bao, Riyang
Yang, Cheng
Yu, Dazhou
Tang, Zhexiang
Mai, Gengchen
Zhao, Liang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_16965
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Spatial-Agent: Agentic Geo-spatial Reasoning with Scientific Core Concepts
Bao, Riyang
Yang, Cheng
Yu, Dazhou
Tang, Zhexiang
Mai, Gengchen
Zhao, Liang
Artificial Intelligence
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.
title Spatial-Agent: Agentic Geo-spatial Reasoning with Scientific Core Concepts
topic Artificial Intelligence
url https://arxiv.org/abs/2601.16965