STEP-LLM: Generating CAD STEP Models from Natural Language with Large Language Models

2026-01-19

AI Summary

This work addresses the limited manufacturability of CAD models generated by existing text-to-CAD methods, which hinders their direct use in industrial production. The study presents the first end-to-end framework that generates standard STEP-format CAD models directly from natural language descriptions. It introduces a depth-first re-serialization strategy tailored to the graph-structured nature of STEP data, coupled with a structure-guided generation approach. The method further integrates chain-of-thought annotations, retrieval-augmented generation, and geometry-aware reinforcement learning based on Chamfer distance. Experimental results demonstrate substantial improvements over Text2CAD baselines in geometric fidelity, model completeness, and renderability, establishing the feasibility of leveraging large language models for high-fidelity, manufacturing-ready CAD generation.

Technology Category

• Natural Language Processing: Generation
• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Computer-aided design (CAD) is vital to modern manufacturing, yet model creation remains labor-intensive and expertise-heavy. To enable non-experts to translate intuitive design intent into manufacturable artifacts, recent large language models-based text-to-CAD efforts focus on command sequences or script-based formats like CadQuery. However, these formats are kernel-dependent and lack universality for manufacturing. In contrast, the Standard for the Exchange of Product Data (STEP, ISO 10303) file is a widely adopted, neutral boundary representation (B-rep) format directly compatible with manufacturing, but its graph-structured, cross-referenced nature poses unique challenges for auto-regressive LLMs. To address this, we curate a dataset of ~40K STEP-caption pairs and introduce novel preprocessing tailored for the graph-structured format of STEP, including a depth-first search-based reserialization that linearizes cross-references while preserving locality and chain-of-thought(CoT)-style structural annotations that guide global coherence. We integrate retrieval-augmented generation to ground predictions in relevant examples for supervised fine-tuning, and refine generation quality through reinforcement learning with a specific Chamfer Distance-based geometric reward. Experiments demonstrate consistent gains of our STEP-LLM in geometric fidelity over the Text2CAD baseline, with improvements arising from multiple stages of our framework: the RAG module substantially enhances completeness and renderability, the DFS-based reserialization strengthens overall accuracy, and the RL further reduces geometric discrepancy. Both metrics and visual comparisons confirm that STEP-LLM generates shapes with higher fidelity than Text2CAD. These results show the feasibility of LLM-driven STEP model generation from natural language, showing its potential to democratize CAD design for manufacturing.

Problem

• CAD
• STEP
• natural language
• manufacturing
• B-rep

Innovation

• STEP-LLM
• text-to-CAD
• graph-structured generation
• retrieval-augmented generation
• reinforcement learning with geometric reward