mlsanityData to 7 Oct 2026

BlenderRAG: High-Fidelity 3D Object Generation via Retrieval-Augmented Code Synthesis

arXiv 2605.00632 ↗First posted 1 May 2026cs.CV cs.AI cs.GRcited by 0

On the map: Retrieval-augmented generation → RAG for code

Abstract (arXiv)

Automatic generation of executable Blender code from natural language remains challenging, with state-of-the-art LLMs producing frequent syntactic errors and geometrically inconsistent objects. We present BlenderRAG, a retrieval-augmented generation system that operates on a curated multimodal dataset of 500 expert-validated examples (text, code, image) across 50 object categories. By retrieving semantically similar examples during generation, BlenderRAG improves compilation success rates from 40.8% to 70.0% and semantic normalized alignment from 0.41 to 0.77 (CLIP similarity) across four state-of-the-art LLMs, without requiring fine-tuning or specialized hardware, making it immediately accessible for deployment. The dataset and code will be available at https://github.com/MaxRondelli/BlenderRAG.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in RAG for code, one of 15 directions in Retrieval-augmented generation. Builds on 10 of its 13 references that are in the map. First posted on arXiv 1 May 2026.

Builds on

10 of 13 references.

References · 10

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  3. 2021Program Synthesis with Large Language Modelscited by 3,509
  4. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  5. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  6. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  7. 2023StarCoder: may the source be with you!cited by 790
  8. 20233D-GPT: Procedural 3D Modeling with Large Language Modelscited by 91
  9. 2024SceneCraft: Layout-Guided 3D Scene Generationcited by 40
  10. 2024BlenderLLM: Training Large Language Models for Computer-Aided Design with Self-improvementcited by 26

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds
  2. 2025LL3M: Large Language 3D Modelers
  3. 20253DFroMLLM: 3D Prototype Generation only from Pretrained Multimodal LLMs
  4. 20263D-CoS: A New 3D Reconstruction Paradigm Based on VLM Code Synthesis
  5. 2024A Survey On Text-to-3D Contents Generation In The Wild
  6. 2026P3D-Bench: Benchmarking MLLMs for Parametric 3D Generation and Structural Reasoning
  7. 2026PartRAG: Retrieval-Augmented Part-Level 3D Generation and Editing
  8. 2024Generating CAD Code with Vision-Language Models for 3D Designs