# BlenderLLM: Training Large Language Models for Computer-Aided Design with Self-improvement

arXiv: https://arxiv.org/abs/2412.14203 · HTML: https://mlsanity.com/paper/2412.14203/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Placed in Self-rewarding alignment and self-training, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 15 of its 32 references that are in the map.
- First posted on arXiv 16 Dec 2024.

## Placed in

- Synthetic data and self-improvement for LLMs / [Self-rewarding alignment and self-training](https://mlsanity.com/synth/self-rewarding-alignment-and-self-training/)

## Builds on (most cited first, 15 of 15)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [CadVLM: Bridging Language and Vision in the Generation of Parametric CAD Sketches](https://mlsanity.com/paper/2409.17457/) (2024)
- [MLLM-Bench: Evaluating Multimodal LLMs with Per-sample Criteria](https://mlsanity.com/paper/2311.13951/) (2023)
- [3D-PreMise: Can Large Language Models Generate 3D Shapes with Sharp Features and Parametric Control?](https://mlsanity.com/paper/2401.06437/) (2024)
- [Sketch2CAD: Sequential CAD Modeling by Sketching in Context](https://mlsanity.com/paper/2009.04927/) (2020)
- [CADgpt: Harnessing Natural Language Processing for 3D Modelling to Enhance Computer-Aided Design Workflows](https://mlsanity.com/paper/2401.05476/) (2024)

## Built on by (most cited first, 29 of 29)

- [CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generation](https://mlsanity.com/paper/2505.14646/) (2025)
- [Large Language Models for Computer-Aided Design: A Survey](https://mlsanity.com/paper/2505.08137/) (2025)
- [3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code](https://mlsanity.com/paper/2606.01057/) (2026)
- [CADBench: A Multimodal Benchmark for AI-Assisted CAD Program Generation](https://mlsanity.com/paper/2605.10873/) (2026)
- [SceneCode: Executable World Programs for Editable Indoor Scenes with Articulated Objects](https://mlsanity.com/paper/2605.19587/) (2026)
- [Automated CAD Modeling Sequence Generation from Text Descriptions via Transformer-Based Large Language Models](https://mlsanity.com/paper/2505.19490/) (2025)
- [VoxelCodeBench: Benchmarking 3D World Modeling Through Code Generation](https://mlsanity.com/paper/2604.02580/) (2026)
- [A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data](https://mlsanity.com/paper/2601.17717/) (2026)
- [TOOLCAD: Exploring Tool-Using Large Language Models in Text-to-CAD Generation with Reinforcement Learning](https://mlsanity.com/paper/2604.07960/) (2026)
- [ShapeLib: Designing a library of programmatic 3D shape abstractions with Large Language Models](https://mlsanity.com/paper/2502.08884/) (2025)
- [ToolGrad: Efficient Tool-use Dataset Generation with Textual "Gradients"](https://mlsanity.com/paper/2508.04086/) (2025)
- [ShapeCraft: LLM Agents for Structured, Textured and Interactive 3D Modeling](https://mlsanity.com/paper/2510.17603/) (2025)
- [Nova3D: Code-Native Generation of Programmable 3D Assets](https://mlsanity.com/paper/2607.22738/) (2026)
- [3DFroMLLM: 3D Prototype Generation only from Pretrained Multimodal LLMs](https://mlsanity.com/paper/2508.08821/) (2025)
- [BrepLLM: Enabling Large Language Models to Understand Boundary Representations](https://mlsanity.com/paper/2512.16413/) (2025)
- [From Idea to Co-Creation: A Planner-Actor-Critic Framework for Agent Augmented 3D Modeling](https://mlsanity.com/paper/2601.05016/) (2026)
- [Aggregating LLM-Based Weak Verifiers for Spatial Layout Generation](https://mlsanity.com/paper/2606.05268/) (2026)
- [3D-CoS: A New 3D Reconstruction Paradigm Based on VLM Code Synthesis](https://mlsanity.com/paper/2606.10478/) (2026)
- [BIM-Edit: Benchmarking Large Language Models for IFC-Based Building Information Modeling](https://mlsanity.com/paper/2606.20146/) (2026)
- [aDSL: Agentic 3D Creation via Joint Agent-Program Design](https://mlsanity.com/paper/2608.17975/) (2026)
- [ViSculpt: Visual-Centric Agentic Geometry Editing](https://mlsanity.com/paper/2608.24169/) (2026)
- [3DHarnessBench: Probing Agentic 3D-to-Code Capabilities of Frontier Vision-Language Models](https://mlsanity.com/paper/2609.06535/) (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)
- [See2Refine: Vision-Language Feedback Improves LLM-Based eHMI Action Designers](https://mlsanity.com/paper/2602.02063/) (2026)
- [Bioinspired123D: Generative 3D Modeling System for Bioinspired Structures](https://mlsanity.com/paper/2603.29592/) (2026)
- [Learning Hierarchical and Geometry-Aware Graph Representations for Text-to-CAD](https://mlsanity.com/paper/2604.10075/) (2026)
- [BlenderRAG: High-Fidelity 3D Object Generation via Retrieval-Augmented Code Synthesis](https://mlsanity.com/paper/2605.00632/) (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)

The application of Large Language Models (LLMs) in Computer-Aided Design (CAD) remains an underexplored area, despite their remarkable advancements in other domains. In this paper, we present BlenderLLM, a novel framework for training LLMs specifically for CAD tasks leveraging a self-improvement methodology. To support this, we developed a bespoke training dataset, BlendNet, and introduced a comprehensive evaluation suite, CADBench. Our results reveal that existing models demonstrate significant limitations in generating accurate CAD scripts. However, through minimal instruction-based fine-tuning and iterative self-improvement, BlenderLLM significantly surpasses these models in both functionality and accuracy of CAD script generation. This research establishes a strong foundation for the application of LLMs in CAD while demonstrating the transformative potential of self-improving models in advancing CAD automation. We encourage further exploration and adoption of these methodologies to drive innovation in the field. The dataset, model, benchmark, and source code are publicly available at https://github.com/FreedomIntelligence/BlenderLLM