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

arXiv: https://arxiv.org/abs/2509.21593 · HTML: https://mlsanity.com/paper/2509.21593/

## Key facts

- Cited by 1 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 21 of its 33 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Placed in

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

## Builds on (most cited first, 21 of 21)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [Active Retrieval Augmented Generation](https://mlsanity.com/paper/2305.06983/) (2023)
- [On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence](https://mlsanity.com/paper/2304.06798/) (2023)
- [Algorithm Discovery With LLMs: Evolutionary Search Meets Reinforcement Learning](https://mlsanity.com/paper/2504.05108/) (2025)
- [RAG-Fusion: a New Take on Retrieval-Augmented Generation](https://mlsanity.com/paper/2402.03367/) (2024)
- [Discovering Preference Optimization Algorithms with and for Large Language Models](https://mlsanity.com/paper/2406.08414/) (2024)
- [Large Language Model for Participatory Urban Planning](https://mlsanity.com/paper/2402.17161/) (2024)
- [Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agents](https://mlsanity.com/paper/2501.13299/) (2025)
- [Improving Scientific Hypothesis Generation with Knowledge Grounded Large Language Models](https://mlsanity.com/paper/2411.02382/) (2024)
- [An LLM Agent for Automatic Geospatial Data Analysis](https://mlsanity.com/paper/2410.18792/) (2024)
- [LLM Guided Evolution -- The Automation of Models Advancing Models](https://mlsanity.com/paper/2403.11446/) (2024)
- [Amplifying human performance in combinatorial competitive programming](https://mlsanity.com/paper/2411.19744/) (2024)
- [Large Language Model (LLM) for Standard Cell Layout Design Optimization](https://mlsanity.com/paper/2406.06549/) (2024)
- [GeoConformal prediction: a model-agnostic framework of measuring the uncertainty of spatial prediction](https://mlsanity.com/paper/2412.08661/) (2024)
- [Feature-free regression kriging](https://mlsanity.com/paper/2507.07382/) (2025)

## Built on by (most cited first, 1 of 1)

- [RemoteShield: Enable Robust Multimodal Large Language Models for Earth Observation](https://mlsanity.com/paper/2604.17243/) (2026)

## Abstract (arXiv)

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.