# Code2Worlds: Empowering Coding LLMs for 4D World Generation

arXiv: https://arxiv.org/abs/2602.11757 · HTML: https://mlsanity.com/paper/2602.11757/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 30 references that are in the map.
- First posted on arXiv 12 Feb 2026.

## Builds on (most cited first, 23 of 23)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs](https://mlsanity.com/paper/2401.11708/) (2024)
- [DreamGaussian4D: Generative 4D Gaussian Splatting](https://mlsanity.com/paper/2312.17142/) (2023)
- [Infinite Photorealistic Worlds using Procedural Generation](https://mlsanity.com/paper/2306.09310/) (2023)
- [Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation](https://mlsanity.com/paper/2406.11824/) (2024)
- [SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code](https://mlsanity.com/paper/2403.01248/) (2024)
- [3D-GPT: Procedural 3D Modeling with Large Language Models](https://mlsanity.com/paper/2310.12945/) (2023)
- [MindAgent: Emergent Gaming Interaction](https://mlsanity.com/paper/2309.09971/) (2023)
- [SinFusion: Training Diffusion Models on a Single Image or Video](https://mlsanity.com/paper/2211.11743/) (2022)
- [Grid Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2404.00234/) (2024)
- [MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds](https://mlsanity.com/paper/2508.14879/) (2025)
- [Procedural Generation of Articulated Simulation-Ready Assets](https://mlsanity.com/paper/2505.10755/) (2025)
- [ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxies](https://mlsanity.com/paper/2506.14315/) (2025)
- [VULCAN: Tool-Augmented Multi Agents for Iterative 3D Object Arrangement](https://mlsanity.com/paper/2512.22351/) (2025)

## Built on by (most cited first, 19 of 19)

- [Code as Agent Harness](https://mlsanity.com/paper/2605.18747/) (2026)
- [LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models](https://mlsanity.com/paper/2603.07145/) (2026)
- [SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning](https://mlsanity.com/paper/2605.09423/) (2026)
- [MWM: Mobile World Models for Action-Conditioned Consistent Prediction](https://mlsanity.com/paper/2603.07799/) (2026)
- [One Video, One World: Turning Monocular Video into Physical 4D Scenes](https://mlsanity.com/paper/2606.31388/) (2026)
- [Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models](https://mlsanity.com/paper/2608.25518/) (2026)
- [4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes](https://mlsanity.com/paper/2610.03715/) (2026)
- [UniMesh: Unifying 3D Mesh Understanding and Generation](https://mlsanity.com/paper/2604.17472/) (2026)
- [Bunraku: Turning a Single Illustration into an Editable Live2D Character](https://mlsanity.com/paper/2607.27348/) (2026)
- [ProcFunc: Function-Oriented Abstractions for Procedural 3D Generation in Python](https://mlsanity.com/paper/2604.26943/) (2026)
- [HappyWorld-Bench](https://mlsanity.com/paper/2609.24308/) (2026)
- [WorldAgent: Verification-Guided Agentic Physical World Construction](https://mlsanity.com/paper/2609.33208/) (2026)
- [WorldWeave: Growing Persistent Geometric Worlds for Video Generation](https://mlsanity.com/paper/2609.34221/) (2026)
- [Code2Games: Enabling Coding Agents for Gaming World Generation](https://mlsanity.com/paper/2610.05033/) (2026)
- [AgentGarten: Code Worlds for Evolving Agents](https://mlsanity.com/paper/2610.12374/) (2026)
- [ExeWorldBench: Benchmarking Code-Based Executable 3D World Modeling](https://mlsanity.com/paper/2610.15166/) (2026)
- [CineRecon: Benchmarking Frontier Models for Agentic Cinematic Reconstruction](https://mlsanity.com/paper/2610.16577/) (2026)
- [PhysCodeGym: Benchmarking Coding Agents for Physically Verifiable 4D Reconstruction](https://mlsanity.com/paper/2610.17288/) (2026)
- [Code2Worlds-2: Physically Plausible Agent Harness for Embodied World Simulation](https://mlsanity.com/paper/2610.17651/) (2026)

## Abstract (arXiv)

Achieving spatial intelligence requires moving beyond visual plausibility to build world simulators grounded in physical laws. While coding LLMs have advanced static 3D scene generation, extending this paradigm to 4D dynamics remains a critical frontier. This task presents two fundamental challenges: multi-scale context entanglement, where monolithic generation fails to balance local object structures with global environmental layouts; and a semantic-physical execution gap, where open-loop code generation leads to physical hallucinations lacking dynamic fidelity. We introduce Code2Worlds, a framework that formulates 4D generation as language-to-simulation code generation. First, we propose a dual-stream architecture that disentangles retrieval-augmented object generation from hierarchical environmental orchestration. Second, to ensure dynamic fidelity, we establish a physics-aware closed-loop mechanism in which a PostProcess Agent scripts dynamics, coupled with a VLM-Motion Critic that performs self-reflection to iteratively refine simulation code. Evaluations on the Code4D benchmark show Code2Worlds outperforms baselines with a 41% SGS gain and 49% higher Richness, while uniquely generating physics-aware dynamics absent in prior static methods. Code: https://github.com/AIGeeksGroup/Code2Worlds. Website: https://aigeeksgroup.github.io/Code2Worlds.