GeoEvolve: Automating Geospatial Model Discovery via Multi-Agent Large Language Models

2025-09-25

AI Summary

Existing LLM-based algorithm discovery frameworks (e.g., AlphaEvolve) lack domain-specific geospatial knowledge and multi-step reasoning capabilities, limiting their applicability to critical sustainability and climate change modeling tasks. To address this, we propose GeoEvolve—the first multi-agent LLM framework tailored for geospatial modeling. It introduces a novel nested dual-loop evolutionary architecture and integrates the geospatial knowledge base GeoKnowRAG to inject theoretical priors, enabling knowledge-driven, interpretable, and efficient automated algorithm discovery. Our method synergistically combines multi-agent collaboration, evolutionary search, retrieval-augmented generation (RAG), and geoinformation theory, establishing a joint optimization mechanism for code evolution and global control. Evaluated on spatial interpolation and uncertainty quantification, GeoEvolve reduces interpolation error by 13–21% and improves uncertainty estimation performance by 17%, demonstrating its effectiveness, robustness, and cross-task transferability.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Search and Optimization: Evolutionary Computation
• Machine Learning: Evolutionary Learning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Geospatial modeling provides critical solutions for pressing global challenges such as sustainability and climate change. Existing large language model (LLM)-based algorithm discovery frameworks, such as AlphaEvolve, excel at evolving generic code but lack the domain knowledge and multi-step reasoning required for complex geospatial problems. We introduce GeoEvolve, a multi-agent LLM framework that couples evolutionary search with geospatial domain knowledge to automatically design and refine geospatial algorithms. GeoEvolve operates in two nested loops: an inner loop leverages a code evolver to generate and mutate candidate solutions, while an outer agentic controller evaluates global elites and queries a GeoKnowRAG module -- a structured geospatial knowledge base that injects theoretical priors from geography. This knowledge-guided evolution steers the search toward theoretically meaningful and computationally efficient algorithms. We evaluate GeoEvolve on two fundamental and classical tasks: spatial interpolation (kriging) and spatial uncertainty quantification (geospatial conformal prediction). Across these benchmarks, GeoEvolve automatically improves and discovers new algorithms, incorporating geospatial theory on top of classical models. It reduces spatial interpolation error (RMSE) by 13-21% and enhances uncertainty estimation performance by 17%. Ablation studies confirm that domain-guided retrieval is essential for stable, high-quality evolution. These results demonstrate that GeoEvolve provides a scalable path toward automated, knowledge-driven geospatial modeling, opening new opportunities for trustworthy and efficient AI-for-Science discovery.

Problem

• Automating geospatial model discovery using multi-agent LLMs
• Incorporating domain knowledge to improve geospatial algorithm design
• Enhancing spatial interpolation and uncertainty quantification accuracy

Innovation

• Multi-agent LLM framework combines evolutionary search with geospatial knowledge
• Two nested loops generate candidates and evaluate with domain knowledge
• Knowledge-guided evolution improves spatial interpolation and uncertainty quantification