# UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City

arXiv: https://arxiv.org/abs/2608.27456 · HTML: https://mlsanity.com/paper/2608.27456/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 40 of its 48 references that are in the map.
- First posted on arXiv 27 Aug 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 40)

- [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022)
- [NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation](https://mlsanity.com/paper/2402.15852/) (2024)
- [EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents](https://mlsanity.com/paper/2502.09560/) (2025)
- [NaVILA: Legged Robot Vision-Language-Action Model for Navigation](https://mlsanity.com/paper/2412.04453/) (2024)
- [JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models](https://mlsanity.com/paper/2311.05997/) (2023)
- [BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games](https://mlsanity.com/paper/2411.13543/) (2024)
- [Cradle: Empowering Foundation Agents Towards General Computer Control](https://mlsanity.com/paper/2403.03186/) (2024)
- [Embodied Navigation Foundation Model](https://mlsanity.com/paper/2509.12129/) (2025)
- [VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View](https://mlsanity.com/paper/2307.06082/) (2023)
- [Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity](https://mlsanity.com/paper/2607.00248/) (2026)
- [lmgame-Bench: How Good are LLMs at Playing Games?](https://mlsanity.com/paper/2505.15146/) (2025)
- [GROOT: Learning to Follow Instructions by Watching Gameplay Videos](https://mlsanity.com/paper/2310.08235/) (2023)
- [CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos](https://mlsanity.com/paper/2411.17820/) (2024)
- [VideoGameBench: Can Vision-Language Models complete popular video games?](https://mlsanity.com/paper/2505.18134/) (2025)
- [V-IRL: Grounding Virtual Intelligence in Real Life](https://mlsanity.com/paper/2402.03310/) (2024)
- [MCU: An Evaluation Framework for Open-Ended Game Agents](https://mlsanity.com/paper/2310.08367/) (2023)
- [GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents](https://mlsanity.com/paper/2604.26752/) (2026)
- [CityNavAgent: Aerial Vision-and-Language Navigation with Hierarchical Semantic Planning and Global Memory](https://mlsanity.com/paper/2505.05622/) (2025)
- [Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games](https://mlsanity.com/paper/2506.03610/) (2025)
- [GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents](https://mlsanity.com/paper/2604.07429/) (2026)
- [Odyssey: Empowering Minecraft Agents with Open-World Skills](https://mlsanity.com/paper/2407.15325/) (2024)
- [iVISPAR -- An Interactive Visual-Spatial Reasoning Benchmark for VLMs](https://mlsanity.com/paper/2502.03214/) (2025)
- [UrbanWorld: An Urban World Model for 3D City Generation](https://mlsanity.com/paper/2407.11965/) (2024)
- [NavBench: Probing Multimodal Large Language Models for Embodied Navigation](https://mlsanity.com/paper/2506.01031/) (2025)
- [A Survey on Agentic Multimodal Large Language Models](https://mlsanity.com/paper/2510.10991/) (2025)
- [MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility](https://mlsanity.com/paper/2407.08725/) (2024)
- [Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds](https://mlsanity.com/paper/2511.08892/) (2025)
- [ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting](https://mlsanity.com/paper/2410.17856/) (2024)
- [VLNVerse: A Benchmark for Vision-Language Navigation with Versatile, Embodied, Realistic Simulation and Evaluation](https://mlsanity.com/paper/2512.19021/) (2025)
- [UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence with Spatial Reasoning and Understanding](https://mlsanity.com/paper/2506.23219/) (2025)

## Built on by (most cited first, 1 of 1)

- [Mine Odyssey: Benchmarking Spatial Agentic Intelligence in the Wild](https://mlsanity.com/paper/2610.11328/) (2026)

## Abstract (arXiv)

Multimodal large language models (MLLMs) can interpret a street view, but reliable urban action depends on whether such local evidence remains useful after the agent starts to move. In this paper, we investigate how far current MLLM agents can turn local urban perception into reliable action in a real-scale city. We propose UrbanGround, an urban sandbox built from Hong Kong's territory-wide 3D geospatial data. It combines the city's geographic structure with continuous, collision-constrained control through a shared evaluation interface. Agents use first-person observations and an interactive map to select actions across tasks ranging from local question answering to long-horizon navigation. Our analysis follows the growth of the spatial problem through three research questions. We first test whether an agent can gather and interpret local visual evidence to answer spatial questions. Then we ask whether these abilities support navigation as destinations become farther away and less explicit. Finally, we examine whether the resulting behavior survives changes in route availability and pedestrian motion. MLLM agents usually show useful atomic abilities in visual recognition and short-range spatial reasoning, while orientation and pedestrian-aware movement remain unreliable. Their central failure emerges over extended exploration, where local abilities do not compose into sustained goal-directed behavior and errors accumulate without effective correction. We hope UrbanGround will support broader study of how far MLLM agents can explore reliably in open-ended urban environments.