GeoFlow: Agentic Workflow Automation for Geospatial Tasks

TL;DR

GeoFlow is a novel method that automatically creates agentic workflows for geospatial tasks, improving success rates and reducing token usage by guiding API calls at runtime.

Contribution

It introduces detailed tool-calling objectives for agents, enhancing geospatial task automation and efficiency over prior reasoning-focused methods.

Findings

Increases agentic success by 6.8%.

Reduces token usage up to fourfold.

Applicable across major LLM families.

Abstract

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.