{"ID":2886068,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.04719","arxiv_id":"2508.04719","title":"GeoFlow: Agentic Workflow Automation for Geospatial Tasks","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.","short_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 incre...","url_abs":"https://arxiv.org/abs/2508.04719","url_pdf":"https://arxiv.org/pdf/2508.04719v1","authors":"[\"Amulya Bhattaram\",\"Justin Chung\",\"Stanley Chung\",\"Ranit Gupta\",\"Janani Ramamoorthy\",\"Kartikeya Gullapalli\",\"Diana Marculescu\",\"Dimitrios Stamoulis\"]","published":"2025-08-05T02:14:58Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.LG\"]","methods":"[\"Large Language Model\"]","has_code":false}