ShapefileGPT: A Multi-Agent Large Language Model Framework for Automated Shapefile Processing

TL;DR

ShapefileGPT is a multi-agent LLM framework that automates Shapefile processing, overcoming traditional LLM limitations in GIS data analysis, and achieving high success rates in complex spatial tasks.

Contribution

The paper introduces a novel multi-agent LLM framework tailored for Shapefile tasks, including a specialized function library and a benchmark dataset, significantly improving automation in GIS vector data analysis.

Findings

Achieved 95.24% task success rate, outperforming GPT models.

Effectively handles complex spatial and topological relationships.

Enables automation of GIS vector data processing for interdisciplinary research.

Abstract

Vector data is one of the two core data structures in geographic information science (GIS), essential for accurately storing and representing geospatial information. Shapefile, the most widely used vector data format, has become the industry standard supported by all major geographic information systems. However, processing this data typically requires specialized GIS knowledge and skills, creating a barrier for researchers from other fields and impeding interdisciplinary research in spatial data analysis. Moreover, while large language models (LLMs) have made significant advancements in natural language processing and task automation, they still face challenges in handling the complex spatial and topological relationships inherent in GIS vector data. To address these challenges, we propose ShapefileGPT, an innovative framework powered by LLMs, specifically designed to automate Shapefile tasks. ShapefileGPT utilizes a multi-agent architecture, in which the planner agent is responsible for task decomposition and supervision, while the worker agent executes the tasks. We developed a specialized function library for handling Shapefiles and provided comprehensive API documentation, enabling the worker agent to operate Shapefiles efficiently through function calling. For evaluation, we developed a benchmark dataset based on authoritative textbooks, encompassing tasks in categories such as geometric operations and spatial queries. ShapefileGPT achieved a task success rate of 95.24%, outperforming the GPT series models. In comparison to traditional LLMs, ShapefileGPT effectively handles complex vector data analysis tasks, overcoming the limitations of traditional LLMs in spatial analysis. This breakthrough opens new pathways for advancing automation and intelligence in the GIS field, with significant potential in interdisciplinary data analysis and application contexts.