GeoAI Agency Primitives
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917380190371840 |
|---|---|
| author | Zaytar, Akram Sawahn, Rohan Robinson, Caleb Hacheme, Gilles Q. Tadesse, Girmaw A. Becker-Reshef, Inbal Dodhia, Rahul Ferres, Juan Lavista |
| author_facet | Zaytar, Akram Sawahn, Rohan Robinson, Caleb Hacheme, Gilles Q. Tadesse, Girmaw A. Becker-Reshef, Inbal Dodhia, Rahul Ferres, Juan Lavista |
| contents | We present ongoing research on agency primitives for GeoAI assistants -- core capabilities that connect Foundation models to the artifact-centric, human-in-the-loop workflows where GIS practitioners actually work. Despite advances in satellite image captioning, visual question answering, and promptable segmentation, these capabilities have not translated into productivity gains for practitioners who spend most of their time producing vector layers, raster maps, and cartographic products. The gap is not model capability alone but the absence of an agency layer that supports iterative collaboration. We propose a vocabulary of $9$ primitives for such a layer -- including navigation, perception, geo-referenced memory, and dual modeling -- along with a benchmark that measures human productivity. Our goal is a vocabulary that makes agentic assistance in GIS implementable, testable, and comparable. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_01869 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GeoAI Agency Primitives Zaytar, Akram Sawahn, Rohan Robinson, Caleb Hacheme, Gilles Q. Tadesse, Girmaw A. Becker-Reshef, Inbal Dodhia, Rahul Ferres, Juan Lavista Computer Vision and Pattern Recognition We present ongoing research on agency primitives for GeoAI assistants -- core capabilities that connect Foundation models to the artifact-centric, human-in-the-loop workflows where GIS practitioners actually work. Despite advances in satellite image captioning, visual question answering, and promptable segmentation, these capabilities have not translated into productivity gains for practitioners who spend most of their time producing vector layers, raster maps, and cartographic products. The gap is not model capability alone but the absence of an agency layer that supports iterative collaboration. We propose a vocabulary of $9$ primitives for such a layer -- including navigation, perception, geo-referenced memory, and dual modeling -- along with a benchmark that measures human productivity. Our goal is a vocabulary that makes agentic assistance in GIS implementable, testable, and comparable. |
| title | GeoAI Agency Primitives |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.01869 |