[2603.26845] GISclaw: An Open-Source LLM-Powered Agent System for Full-Stack Geospatial Analysis

Computer Science > Software Engineering arXiv:2603.26845 (cs) [Submitted on 27 Mar 2026] Title:GISclaw: An Open-Source LLM-Powered Agent System for Full-Stack Geospatial Analysis Authors:Jinzhen Han, JinByeong Lee, Yuri Shim, Jisung Kim, Jae-Joon Lee View a PDF of the paper titled GISclaw: An Open-Source LLM-Powered Agent System for Full-Stack Geospatial Analysis, by Jinzhen Han and 4 other authors View PDF HTML (experimental) Abstract:The convergence of Large Language Models (LLMs) and Geographic Information Science has opened new avenues for automating complex geospatial analysis. However, existing LLM-powered GIS agents are constrained by limited data-type coverage (vector-only), reliance on proprietary GIS platforms, and single-model architectures that preclude systematic comparisons. We present GISclaw, an open-source agent system that integrates an LLM reasoning core with a persistent Python sandbox, a comprehensive suite of open-source GIS libraries (GeoPandas, rasterio, scipy, scikit-learn), and a web-based interactive interface for full-stack geospatial analysis spanning vector, raster, and tabular data. GISclaw implements two pluggable agent architectures -- a Single Agent ReAct loop and a Dual Agent Plan-Execute-Replan pipeline -- and supports six heterogeneous LLM backends ranging from cloud-hosted flagship models (GPT-5.4) to locally deployed 14B models on consumer GPUs. Through three key engineering innovations -- Schema Analysis bridging the task-data inform...