# LL3M: Large Language 3D Modelers

arXiv: https://arxiv.org/abs/2508.08228 · HTML: https://mlsanity.com/paper/2508.08228/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 66 references that are in the map.
- First posted on arXiv 11 Aug 2025.

## Builds on (most cited first, 30 of 51)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (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)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [LION: Latent Point Diffusion Models for 3D Shape Generation](https://mlsanity.com/paper/2210.06978/) (2022)
- [3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models](https://mlsanity.com/paper/2301.11445/) (2023)
- [CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields](https://mlsanity.com/paper/2112.05139/) (2021)
- [Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion](https://mlsanity.com/paper/2212.06135/) (2022)
- [Text-to-3D using Gaussian Splatting](https://mlsanity.com/paper/2309.16585/) (2023)
- [PolyGen: An Autoregressive Generative Model of 3D Meshes](https://mlsanity.com/paper/2002.10880/) (2020)
- [MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers](https://mlsanity.com/paper/2311.15475/) (2023)
- [GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models](https://mlsanity.com/paper/2310.08529/) (2023)
- [MeshDiffusion: Score-based Generative 3D Mesh Modeling](https://mlsanity.com/paper/2303.08133/) (2023)
- [MapCoder: Multi-Agent Code Generation for Competitive Problem Solving](https://mlsanity.com/paper/2405.11403/) (2024)
- [MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers](https://mlsanity.com/paper/2406.10163/) (2024)
- [SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code](https://mlsanity.com/paper/2403.01248/) (2024)
- [CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings](https://mlsanity.com/paper/2501.01257/) (2025)
- [NeRF-VAE: A Geometry Aware 3D Scene Generative Model](https://mlsanity.com/paper/2104.00587/) (2021)
- [MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization](https://mlsanity.com/paper/2408.02555/) (2024)
- [3D-GPT: Procedural 3D Modeling with Large Language Models](https://mlsanity.com/paper/2310.12945/) (2023)
- [SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generation](https://mlsanity.com/paper/2206.12055/) (2022)
- [LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation](https://mlsanity.com/paper/2403.12019/) (2024)
- [Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scale](https://mlsanity.com/paper/2412.09548/) (2024)
- [Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modeling](https://mlsanity.com/paper/2505.14521/) (2025)
- [3D-LDM: Neural Implicit 3D Shape Generation with Latent Diffusion Models](https://mlsanity.com/paper/2212.00842/) (2022)
- [PolyDiff: Generating 3D Polygonal Meshes with Diffusion Models](https://mlsanity.com/paper/2312.11417/) (2023)
- [GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning](https://mlsanity.com/paper/2311.12631/) (2023)

## Built on by (most cited first, 20 of 20)

- [SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes](https://mlsanity.com/paper/2602.09153/) (2026)
- [3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code](https://mlsanity.com/paper/2606.01057/) (2026)
- [CoRe3D: Collaborative Reasoning as a Foundation for 3D Intelligence](https://mlsanity.com/paper/2512.12768/) (2025)
- [P3D-Bench: Benchmarking MLLMs for Parametric 3D Generation and Structural Reasoning](https://mlsanity.com/paper/2606.11152/) (2026)
- [SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation](https://mlsanity.com/paper/2607.01766/) (2026)
- [WorldClaw: Agentic 3D Open-World Generation at Scale](https://mlsanity.com/paper/2608.05248/) (2026)
- [Feedforward 3D Editing via Text-Steerable Image-to-3D](https://mlsanity.com/paper/2512.13678/) (2025)
- [Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis](https://mlsanity.com/paper/2605.18451/) (2026)
- [GS-Agent: Creating 4D Physical Worlds With Generative Simulation](https://mlsanity.com/paper/2607.21522/) (2026)
- [EZBlender: Efficient 3D Editing with Plan-and-ReAct Agent](https://mlsanity.com/paper/2601.07143/) (2026)
- [3Dify: a Framework for Procedural 3D-CG Generation Assisted by LLMs Using MCP and RAG](https://mlsanity.com/paper/2510.04536/) (2025)
- [MCP4IFC: IFC-Based Building Design Using Large Language Models](https://mlsanity.com/paper/2511.05533/) (2025)
- [Training-Free Dense Hand Contact Estimation with Multi-Modal Large Language Models](https://mlsanity.com/paper/2605.05886/) (2026)
- [3D-CoS: A New 3D Reconstruction Paradigm Based on VLM Code Synthesis](https://mlsanity.com/paper/2606.10478/) (2026)
- [3DHarnessBench: Probing Agentic 3D-to-Code Capabilities of Frontier Vision-Language Models](https://mlsanity.com/paper/2609.06535/) (2026)
- [CADForge: Agentic Single-View CAD Reconstruction with Explicit Geometry Reasoning](https://mlsanity.com/paper/2610.04262/) (2026)
- [FloraForge: LLM-Assisted Procedural Generation of Editable and Analysis-Ready 3D Plant Geometric Models For Agricultural Applications](https://mlsanity.com/paper/2512.11925/) (2025)
- [CMAG: Concept-Scaffolded Retrieval for Marketplace Avatar Generation](https://mlsanity.com/paper/2605.18680/) (2026)
- [LiteReality-Agent: An Agentic System for Interactable 3D Indoor Scene Reconstruction](https://mlsanity.com/paper/2610.01863/) (2026)
- [Code2Worlds-2: Physically Plausible Agent Harness for Embodied World Simulation](https://mlsanity.com/paper/2610.17651/) (2026)

## Abstract (arXiv)

We present LL3M, a multi-agent system that leverages pretrained large language models (LLMs) to generate 3D assets by writing interpretable Python code in Blender. We break away from the typical generative approach that learns from a collection of 3D data. Instead, we reformulate shape generation as a code-writing task, enabling greater modularity, editability, and integration with artist workflows. Given a text prompt, LL3M coordinates a team of specialized LLM agents to plan, retrieve, write, debug, and refine Blender scripts that generate and edit geometry and appearance. The generated code works as a high-level, interpretable, human-readable, well-documented representation of scenes and objects, making full use of sophisticated Blender constructs (e.g. B-meshes, geometry modifiers, shader nodes) for diverse, unconstrained shapes, materials, and scenes. This code presents many avenues for further agent and human editing and experimentation via code tweaks or procedural parameters. This medium naturally enables a co-creative loop in our system: agents can automatically self-critique using code and visuals, while iterative user instructions provide an intuitive way to refine assets. A shared code context across agents enables awareness of previous attempts, and a retrieval-augmented generation knowledge base built from Blender API documentation, BlenderRAG, equips agents with examples, types, and functions empowering advanced modeling operations and code correctness. We demonstrate the effectiveness of LL3M across diverse shape categories, style and material edits, and user-driven refinements. Our experiments showcase the power of code as a generative and interpretable medium for 3D asset creation. Our project page is at https://threedle.github.io/ll3m.