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.
Author supplied keywords
Cite
CITATION STYLE
Bhattaram, A., Chung, J., Chung, S., Gupta, R., Ramamoorthy, J., Gullapalli, K., … Stamoulis, D. (2025). GeoFlow: Agentic Workflow Automation for Geospatial Tasks. In 33rd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL 2025 (pp. 1150–1153). Association for Computing Machinery, Inc. https://doi.org/10.1145/3748636.3763217
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.