# UrbanWorld2.0: A Multimodal Agentic Framework for Reality-Aligned 3D World Generation at City-Scale

arXiv: https://arxiv.org/abs/2511.18005 · HTML: https://mlsanity.com/paper/2511.18005/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 65 references that are in the map.
- First posted on arXiv 22 Nov 2025.

## Builds on (most cited first, 28 of 28)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [Uni3D: Exploring Unified 3D Representation at Scale](https://mlsanity.com/paper/2310.06773/) (2023)
- [DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis](https://mlsanity.com/paper/2303.14207/) (2023)
- [Understanding World or Predicting Future? A Comprehensive Survey of World Models](https://mlsanity.com/paper/2411.14499/) (2024)
- [Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material](https://mlsanity.com/paper/2506.15442/) (2025)
- [WonderJourney: Going from Anywhere to Everywhere](https://mlsanity.com/paper/2312.03884/) (2023)
- [Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation](https://mlsanity.com/paper/2406.11824/) (2024)
- [GameGen-X: Interactive Open-world Game Video Generation](https://mlsanity.com/paper/2411.00769/) (2024)
- [Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond](https://mlsanity.com/paper/2405.03520/) (2024)
- [CityDreamer: Compositional Generative Model of Unbounded 3D Cities](https://mlsanity.com/paper/2309.00610/) (2023)
- [Artificial Intelligence in the Creative Industries: A Review](https://mlsanity.com/paper/2007.12391/) (2020)
- [GRUtopia: Dream General Robots in a City at Scale](https://mlsanity.com/paper/2407.10943/) (2024)
- [SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent](https://mlsanity.com/paper/2509.20414/) (2025)
- [Guided Co-Modulated GAN for 360deg Field of View Extrapolation](https://mlsanity.com/paper/2204.07286/) (2022)
- [ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary](https://mlsanity.com/paper/2506.00742/) (2025)
- [CityCraft: A Real Crafter for 3D City Generation](https://mlsanity.com/paper/2406.04983/) (2024)
- [UrbanWorld: An Urban World Model for 3D City Generation](https://mlsanity.com/paper/2407.11965/) (2024)
- [3D Scene Generation: A Survey](https://mlsanity.com/paper/2505.05474/) (2025)
- [Compositional Generative Model of Unbounded 4D Cities](https://mlsanity.com/paper/2501.08983/) (2025)
- [Virtual Community: An Open World for Humans, Robots, and Society](https://mlsanity.com/paper/2508.14893/) (2025)
- [MOSS: A Large-scale Open Microscopic Traffic Simulation System](https://mlsanity.com/paper/2405.12520/) (2024)
- [ShapeCraft: LLM Agents for Structured, Textured and Interactive 3D Modeling](https://mlsanity.com/paper/2510.17603/) (2025)

## Built on by (most cited first, 3 of 3)

- [NuiWorld: Exploring a Scalable Framework for End-to-End Controllable World Generation](https://mlsanity.com/paper/2601.19048/) (2026)
- [SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes](https://mlsanity.com/paper/2605.31148/) (2026)
- [CityCode: Building Agent-Operable 3D Cities from Sparse Aerial Observations](https://mlsanity.com/paper/2610.18342/) (2026)

## Abstract (arXiv)

The automated generation of high-fidelity, city-scale 3D environments remains a formidable challenge with profound academic and industrial implications. However, existing methods struggle to achieve the necessary quality, fidelity, and scalability. To address this, we propose UrbanWorld2.0, a reality-aligned intelligent multimodal synthesis engine that creates detailed, city-scale 3D worlds of high fidelity. We introduce an agentic framework that leverages diverse multimodal foundation tools to acquire real-world knowledge, maintain robust intermediate representations, and construct complex 3D scenes. This agentic design, featuring dynamic data processing, iterative self-reflection and refinement, and the invocation of advanced multimodal tools, minimizes cumulative errors and enhances overall performance. Extensive quantitative experiments and qualitative analyzes validate the superior performance of UrbanWorld2.0 in real-world alignment, shape precision, texture fidelity, and aesthetics level, achieving a win rate of over 86% against existing baselines for overall perceptual quality. This combination of 3D quality, reality alignment, scalability, and seamless compatibility with computer graphics pipelines makes UrbanWorld2.0 a promising foundation for applications in immersive media, embodied intelligence, and world models.