Multi-Agent Geospatial Copilots for Remote Sensing Workflows

2025-01-27

AI Summary

To address the challenges of task complexity, procedural intricacy, and low efficiency and accuracy in remote sensing (RS) education for middle school students, this paper proposes GeoLLM-Squad—the first multi-agent collaborative framework tailored for geospatial education. Built upon AutoGen and our custom GeoLLM-Engine, it decomposes end-to-end RS tasks into specialized agents (e.g., image parsing, feature extraction, semantic reasoning), enabling orthogonal agent orchestration and geospatial problem solving. Unlike monolithic large language model approaches, GeoLLM-Squad maintains robustness as task complexity increases and achieves a 17% improvement in agent execution accuracy over state-of-the-art baselines. The framework has been validated across four real-world application domains: urban monitoring, forest conservation, climate analysis, and agricultural research. It supports modular extensibility and seamless integration with education-oriented RS applications.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

We present GeoLLM-Squad, a geospatial Copilot that introduces the novel multi-agent paradigm to remote sensing (RS) workflows. Unlike existing single-agent approaches that rely on monolithic large language models (LLM), GeoLLM-Squad separates agentic orchestration from geospatial task-solving, by delegating RS tasks to specialized sub-agents. Built on the open-source AutoGen and GeoLLM-Engine frameworks, our work enables the modular integration of diverse applications, spanning urban monitoring, forestry protection, climate analysis, and agriculture studies. Our results demonstrate that while single-agent systems struggle to scale with increasing RS task complexity, GeoLLM-Squad maintains robust performance, achieving a 17% improvement in agentic correctness over state-of-the-art baselines. Our findings highlight the potential of multi-agent AI in advancing RS workflows.

Problem

• Remote Sensing Education
• Middle School Students
• Task Efficiency

Innovation

• GeoLLM-Squad
• Multi-agent Collaboration
• Remote Sensing Education