Finding a specific landmark in a city-scale 3D scene with tens of millions of points usually means ranking every candidate. Urbex instead lets an agent explore like a person would. Title: Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes URL: 🏙️ The problem City-scale 3D scenes can span hundreds of thousands to tens of millions of points per scene, and existing ranking-based methods rely on precomputed instance proposals that don't scale. This work reframes urban localization as something inherently sequential and exploratory. 🔧 The approach A VLM agent uses three tools, landmark query, zoom-in, and oblique rendering, to explore a bird's-eye-view multi-view environment before committing a final bounding box. Trained with GRPO, the reward design combines IoU, center-distance shaping, and step penalties to optimize both accuracy and search efficiency. 📊 Results On the CityRefer benchmark, Hit@1 reaches up to 23.9% versus 14.2% for the baseline, while inference takes just 3.2 seconds versus 32.1 seconds, roughly a 10x speedup. Zero-shot transfer to an unseen urban scene still hits 27.2% Hit@1. 🔍 Remaining challenges Missing a named landmark drops Hit@1 by 10.8 points, while coordinate noise barely matters; and when many same-class objects cluster nearby, local success falls from 64.7% to 25.1%. #SpatialAI# #VLMAgents#

🍋 Experience Hearts2Hearts’ “Lemon Tang” all around #SpatialAudio# with @DolbyAtmos on @AppleMusic 🎧 #Hearts2Hearts# #하츠투하츠# #H2H# #LemonTang# #Hearts2Hearts_LemonTang#

IVE’s Looks Can Kill is now in #SpatialAudio# Feel the music all around you with @Dolby Atmos on @AppleMusic ▶️ #IVE# #아이브# #LooksCanKill# #룩스캔킬#

Step into BOYNEXTDOOR’s world with “HOME: DELUXE” now in #SpatialAudio# with @Dolby Atmos on @AppleMusic 🔗 #BOYNEXTDOOR# #보이넥스트도어# #BND# #HOME_DELUXE# #ANIMAL#

Experience our new release “Moonride” all around in #SpatialAudio# with @Dolby Atmos on @AppleMusic. 🍎 #Hearts2Hearts# #하츠투하츠# #H2H# #Moonride# #Hearts2Hearts_Moonride#