Multi-Agent Geospatial Copilots for Remote Sensing Workflows
This work addresses scalability issues in remote sensing workflows for applications like urban monitoring and climate analysis, representing an incremental advancement by applying a multi-agent paradigm to a known bottleneck.
The paper tackles the challenge of scaling remote sensing workflows with increasing task complexity by introducing GeoLLM-Squad, a multi-agent geospatial Copilot, which achieves a 17% improvement in agentic correctness over state-of-the-art single-agent baselines.
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.