Search papers, labs, and topics across Lattice.
This paper introduces nine agency primitives designed to bridge the gap between foundation model capabilities and the practical workflows of GIS practitioners, who primarily work with vector layers, raster maps, and cartographic products. The authors argue that current GeoAI models lack an agency layer to support iterative human-AI collaboration. They propose a vocabulary of primitives, including navigation, perception, and geo-referenced memory, and introduce a benchmark to measure human productivity gains when using these primitives.
GeoAI assistants remain unproductive because they lack a crucial agency layer for iterative human-AI collaboration, a gap this paper addresses with nine core primitives.
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.
Microsoft Research