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

arXiv:2601.12641 · cs.AI · Submitted 2026-01-19 · Read on arXiv

cs.AI

Submitted: 2026-01-19

Updated: 2026-09-27

Comments: Accepted to the Design, Automation & Test in Europe Conference (DATE) 2026; v2 updated to the accepted manuscript

Code: https://github.com/JasonShiii/STEP-LLM

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• RAG — 22× in this paper · explained in 3 episodes
• Fidelity — 18× in this paper · explained in 2 episodes
• Chamfer Distance — 16× in this paper
• Fine-Tuning — 13× in this paper · explained in 5 episodes
• Scaled Chamfer Distance — 9× in this paper
• Alignment — 8× in this paper · explained in 1 episode
• Reinforcement Learning — 8× in this paper · explained in 4 episodes
• Renderability Rate — 7× in this paper
• Accuracy — 5× in this paper · explained in 1 episode
• Robustness — 5× in this paper · explained in 5 episodes
• Ablation — 4× in this paper · explained in 1 episode
• GRPO — 4× in this paper · explained in 6 episodes
• Median Scaled Chamfer Distance — 4× in this paper
• Point Clouds — 4× in this paper · explained in 2 episodes
• Consistency — 3× in this paper · explained in 3 episodes
• Grounding — 3× in this paper · explained in 3 episodes
• Reward Function — 3× in this paper · explained in 2 episodes
• ACM Transactions on Graphics — 2× in this paper
• Ablation Studies — 2× in this paper · explained in 1 episode
• Adaptation — 2× in this paper · explained in 1 episode
• Average Entity Count — 2× in this paper
• Benchmark — 2× in this paper · explained in 2 episodes
• Completion Rate — 2× in this paper
• Reinforcement Learning (RL) — 2× in this paper · explained in 25 episodes
• Retrieval-Augmented Generation (RAG) — 2× in this paper · explained in 16 episodes
• Supervised Fine-Tuning (SFT) — 2× in this paper · explained in 8 episodes
• Unified Framework — 2× in this paper · explained in 5 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Domain Adaptation — 1× in this paper · explained in 5 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Group Relative Policy Optimization — 1× in this paper
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 5 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Model Merging — 1× in this paper · explained in 2 episodes
• Parameter-Efficient Fine-Tuning — 1× in this paper · explained in 2 episodes
• Prompt Engineering — 1× in this paper · explained in 4 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Reward Shaping — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Text-to-CadQuery: A New Paradigm for CAD Generation with Scalable Large Model Capabilities
• Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning
• SolidGen: An Autoregressive Model for Direct B-rep Synthesis
• Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models
• FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language Models
• CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM
• Img2CAD: Reverse Engineering 3D CAD Models from Images through VLM-Assisted Conditional Factorization
• CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generation
• CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward
• Query2CAD: Generating CAD models using natural language queries
• Empowering Autonomous Driving with Large Language Models: A Safety Perspective
• Shedding Light on VLN Robustness: A Black-box Framework for Indoor Lighting-based Adversarial Attack
• SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of Foundation Model-based Embodied Agents
• A Survey on Large Language Models for Code Generation
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
• The Faiss library
• Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning
• The Lessons of Developing Process Reward Models in Mathematical Reasoning
• Enhancing Inverse Reinforcement Learning through Encoding Dynamic Information in Reward Shaping
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems