Urbex: agentic spatial grounding for city-scale 3D scenes
A new arXiv paper, "Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes" by Yu Wang, Rui Dai, Wei Chen and five other authors, reframes city-scale 3D grounding from candidate ranking into active spatial search. Urbex represents a city-scale scene as an interactive multi-view environment in which a vision-language model agent can query landmarks, zoom into local regions, render oblique views and commit a grounded bounding box; the tool-use policy is optimized with reinforcement learning on CityRefer using smooth localization rewards plus lightweight shaping rewards for exploration. The authors report the best Hit@1 and IoU on CityRefer, candidate-free grounding without ground-truth boxes, substantially faster performance than the strongest city-scale ranking baseline, and improved cross-scene robustness in zero-shot results on STPLS3D-Refer. The paper is listed as accepted to NeurIPS 2026 (23 pages, 10 figures).
By turning city-scale 3D grounding into active agentic search, it removes the need for precomputed instance proposals and could make spatial understanding of large outdoor scenes more efficient.