Article

NeurIPS 2026 Paper Urbex: Agent-Driven City-Scale 3D Spatial Localization

Urbex is an agentic vision-language framework for city-scale 3D scenes that shifts from static ranking based on pre-generated candidate boxes to active spatial search, progressively narrowing the search area through three tools—landmark query, local zoom-in, and oblique view—and uses GRPO reinforcement learning to optimize tool-invocation strategies.

Part of the event: Urbex: An Intelligent Agent Spatial Localization Framework for City-Scale 3D Scenes

This page provides a summary and source link only.