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.
@article{arxiv.2605.00632,
title = {BlenderRAG: High-Fidelity 3D Object Generation via Retrieval-Augmented Code Synthesis},
author = {Massimo Rondelli and Francesco Pivi and Maurizio Gabbrielli},
journal= {arXiv preprint arXiv:2605.00632},
year = {2026}
}