# An LLM Agent for Automatic Geospatial Data Analysis

arXiv: https://arxiv.org/abs/2410.18792 · HTML: https://mlsanity.com/paper/2410.18792/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 44 of its 53 references that are in the map.
- First posted on arXiv 24 Oct 2024.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 44)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions](https://mlsanity.com/paper/2406.15877/) (2024)
- [DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation](https://mlsanity.com/paper/2211.11501/) (2022)
- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [GeoChat: Grounded Large Vision-Language Model for Remote Sensing](https://mlsanity.com/paper/2311.15826/) (2023)
- [Long-context LLMs Struggle with Long In-context Learning](https://mlsanity.com/paper/2404.02060/) (2024)
- [RSGPT: A Remote Sensing Vision Language Model and Benchmark](https://mlsanity.com/paper/2307.15266/) (2023)
- [OctoPack: Instruction Tuning Code Large Language Models](https://mlsanity.com/paper/2308.07124/) (2023)
- [EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain](https://mlsanity.com/paper/2401.16822/) (2024)
- [Planning with Large Language Models for Code Generation](https://mlsanity.com/paper/2303.05510/) (2023)
- [Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B](https://mlsanity.com/paper/2406.07394/) (2024)
- [CodeGemma: Open Code Models Based on Gemma](https://mlsanity.com/paper/2406.11409/) (2024)
- [SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model](https://mlsanity.com/paper/2401.09712/) (2024)
- [Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code](https://mlsanity.com/paper/2404.00971/) (2024)
- [Vision-Language Models in Remote Sensing: Current Progress and Future Trends](https://mlsanity.com/paper/2305.05726/) (2023)
- [CodeRAG-Bench: Can Retrieval Augment Code Generation?](https://mlsanity.com/paper/2406.14497/) (2024)
- [MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible Pipeline](https://mlsanity.com/paper/2401.08190/) (2024)
- [K2: A Foundation Language Model for Geoscience Knowledge Understanding and Utilization](https://mlsanity.com/paper/2306.05064/) (2023)
- [GeoLLM: Extracting Geospatial Knowledge from Large Language Models](https://mlsanity.com/paper/2310.06213/) (2023)
- [Change-Agent: Towards Interactive Comprehensive Remote Sensing Change Interpretation and Analysis](https://mlsanity.com/paper/2403.19646/) (2024)

## Built on by (most cited first, 21 of 21)

- [Large Language Model-based Data Science Agent: A Survey](https://mlsanity.com/paper/2508.02744/) (2025)
- [Multi-Agent Geospatial Copilots for Remote Sensing Workflows](https://mlsanity.com/paper/2501.16254/) (2025)
- [Accelerating Earth Science Discovery via Multi-Agent LLM Systems](https://mlsanity.com/paper/2503.05854/) (2025)
- [Generalizability of Large Language Model-Based Agents: A Comprehensive Survey](https://mlsanity.com/paper/2509.16330/) (2025)
- [GeoFlow: Agentic Workflow Automation for Geospatial Tasks](https://mlsanity.com/paper/2508.04719/) (2025)
- [CangLing-KnowFlow: A Unified Knowledge-and-Flow-fused Agent for Comprehensive Remote Sensing Applications](https://mlsanity.com/paper/2512.15231/) (2025)
- [Spatial-Agent: Agentic Geo-spatial Reasoning with Scientific Core Concepts](https://mlsanity.com/paper/2601.16965/) (2026)
- [TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation](https://mlsanity.com/paper/2603.19039/) (2026)
- [Instructor-Worker Large Language Model System for Policy Recommendation: a Case Study on Air Quality Analysis of the January 2025 Los Angeles Wildfires](https://mlsanity.com/paper/2503.00566/) (2025)
- [Agentic AI in Remote Sensing: Foundations, Taxonomy, and Emerging Systems](https://mlsanity.com/paper/2601.01891/) (2026)
- [A Hierarchical Multi-Agent System for Autonomous Discovery in Geoscientific Data Archives](https://mlsanity.com/paper/2602.21351/) (2026)
- [RingMoClaw: An Experience-Inspired Multi-Agent Framework for Self-Evolving Research in Remote Sensing](https://mlsanity.com/paper/2609.00814/) (2026)
- [Multimodal Behavioral Patterns Analysis with Eye-Tracking and LLM-Based Reasoning](https://mlsanity.com/paper/2507.18252/) (2025)
- [GeoEvolve: Automating Geospatial Model Discovery via Multi-Agent Large Language Models](https://mlsanity.com/paper/2509.21593/) (2025)
- [GISAgentBench: A Practitioner-Sourced Benchmark for Evaluating LLM Agents on GIS Tasks](https://mlsanity.com/paper/2608.01645/) (2026)
- [Sensorium Arc: AI Agent System for Oceanic Data Exploration and Interactive Eco-Art](https://mlsanity.com/paper/2511.15997/) (2025)
- [EVE: A Domain-Specific LLM Framework for Earth Intelligence](https://mlsanity.com/paper/2604.13071/) (2026)
- [Medoid Prototype Alignment for Cross-Plant Unknown Attack Detection in Industrial Control Systems](https://mlsanity.com/paper/2604.25544/) (2026)
- [CMIP-Forge: An Agentic System that Retrieves, Computes, and Self-Reviews Climate Science](https://mlsanity.com/paper/2606.17076/) (2026)
- [A Task-Driven and Quality-Assured Agent Framework for SAR Data Generation](https://mlsanity.com/paper/2606.28896/) (2026)
- [An Agentic Interface for End-to-End Probabilistic Seismic Hazard and Risk Analysis](https://mlsanity.com/paper/2607.16249/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are being used in data science code generation tasks, but they often struggle with complex sequential tasks, leading to logical errors. Their application to geospatial data processing is particularly challenging due to difficulties in incorporating complex data structures and spatial constraints, effectively utilizing diverse function calls, and the tendency to hallucinate less-used geospatial libraries. To tackle these problems, we introduce GeoAgent, a new interactive framework designed to help LLMs handle geospatial data processing more effectively. GeoAgent pioneers the integration of a code interpreter, static analysis, and Retrieval-Augmented Generation (RAG) techniques within a Monte Carlo Tree Search (MCTS) algorithm, offering a novel approach to geospatial data processing. In addition, we contribute a new benchmark specifically designed to evaluate the LLM-based approach in geospatial tasks. This benchmark leverages a variety of Python libraries and includes both single-turn and multi-turn tasks such as data acquisition, data analysis, and visualization. By offering a comprehensive evaluation among diverse geospatial contexts, this benchmark sets a new standard for developing LLM-based approaches in geospatial data analysis tasks. Our findings suggest that relying solely on knowledge of LLM is insufficient for accurate geospatial task programming, which requires coherent multi-step processes and multiple function calls. Compared to the baseline LLMs, the proposed GeoAgent has demonstrated superior performance, yielding notable improvements in function calls and task completion. In addition, these results offer valuable insights for the future development of LLM agents in automatic geospatial data analysis task programming.