GeoFlow: Agentic Workflow Automation for Geospatial Tasks
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912524796952576 |
|---|---|
| author | Bhattaram, Amulya Chung, Justin Chung, Stanley Gupta, Ranit Ramamoorthy, Janani Gullapalli, Kartikeya Marculescu, Diana Stamoulis, Dimitrios |
| author_facet | Bhattaram, Amulya Chung, Justin Chung, Stanley Gupta, Ranit Ramamoorthy, Janani Gullapalli, Kartikeya Marculescu, Diana Stamoulis, Dimitrios |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_04719 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GeoFlow: Agentic Workflow Automation for Geospatial Tasks Bhattaram, Amulya Chung, Justin Chung, Stanley Gupta, Ranit Ramamoorthy, Janani Gullapalli, Kartikeya Marculescu, Diana Stamoulis, Dimitrios Artificial Intelligence Machine Learning 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. |
| title | GeoFlow: Agentic Workflow Automation for Geospatial Tasks |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2508.04719 |