GeoFlow: Agentic Workflow Automation for Geospatial Tasks
This addresses the problem of inefficient and error-prone geospatial task automation for users in fields like mapping and environmental analysis, representing an incremental improvement over existing approaches.
The paper tackles automating geospatial tasks by generating agentic workflows with detailed tool-calling objectives, resulting in a 6.8% increase in agentic success and up to fourfold reduction in token usage compared to state-of-the-art methods.
We present GeoFlow, a method that automatically generates agentic workflows for geospatial tasks. Unlike prior work that focuses on reasoning decomposition and leaves API selection implicit, our method provides each agent with detailed tool-calling objectives to guide geospatial API invocation at runtime. GeoFlow increases agentic success by 6.8% and reduces token usage by up to fourfold across major LLM families compared to state-of-the-art approaches.