# ASSEMCAD: Production-Ready CAD Assembly Generation from Natural Language

arXiv: https://arxiv.org/abs/2607.05123 · HTML: https://mlsanity.com/paper/2607.05123/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 51 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Builds on (most cited first, 18 of 18)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models](https://mlsanity.com/paper/2304.06364/) (2023)
- [Measuring what Matters: Construct Validity in Large Language Model Benchmarks](https://mlsanity.com/paper/2511.04703/) (2025)
- [What Large Language Models Know and What People Think They Know](https://mlsanity.com/paper/2401.13835/) (2024)
- [Human heuristics for AI-generated language are flawed](https://mlsanity.com/paper/2206.07271/) (2022)
- [Human Feedback is not Gold Standard](https://mlsanity.com/paper/2309.16349/) (2023)
- [Knowing About Knowing: An Illusion of Human Competence Can Hinder Appropriate Reliance on AI Systems](https://mlsanity.com/paper/2301.11333/) (2023)
- [Improving Human-AI Collaboration With Descriptions of AI Behavior](https://mlsanity.com/paper/2301.06937/) (2023)
- [Task Supportive and Personalized Human-Large Language Model Interaction: A User Study](https://mlsanity.com/paper/2402.06170/) (2024)
- [Understanding Learner-LLM Chatbot Interactions and the Impact of Prompting Guidelines](https://mlsanity.com/paper/2504.07840/) (2025)
- [What Lies Beneath? Exploring the Impact of Underlying AI Model Updates in AI-Infused Systems](https://mlsanity.com/paper/2311.10652/) (2023)
- [A Map of Exploring Human Interaction patterns with LLM: Insights into Collaboration and Creativity](https://mlsanity.com/paper/2404.04570/) (2024)
- [Human Bias in the Face of AI: Examining Human Judgment Against Text Labeled as AI Generated](https://mlsanity.com/paper/2410.03723/) (2024)
- [Making Sense of AI Limitations: How Individual Perceptions Shape Organizational Readiness for AI Adoption](https://mlsanity.com/paper/2502.15870/) (2025)
- [Understand User Opinions of Large Language Models via LLM-Powered In-the-Moment User Experience Interviews](https://mlsanity.com/paper/2502.15226/) (2025)
- [From Prompting to Partnering: Personalization Features for Human-LLM Interactions](https://mlsanity.com/paper/2503.00681/) (2025)

## Abstract (arXiv)

Recent advances in large language models and programmatic CAD have significantly improved Text-to-CAD generation for individual parts. However, production-ready mechanical assembly generation remains largely unsolved. Unlike single-part modeling, assemblies require coordinated reasoning over multiple components, functional interfaces, assembly relations, engineering principles, and physical consistency. Consequently, directly generating executable CAD code is insufficient for constructing mechanically valid and reusable assemblies. We present AssemCAD, an axiom-grounded framework for production-ready CAD assembly generation from natural language. Instead of representing an assembly as monolithic CAD code, AssemCAD first constructs an axiomatic Assembly Specification consisting of typed parts, geometry-backed ports, executable mates, and engineering axioms. Each assembly relation is explicitly grounded in one or more engineering principles, making the resulting specification interpretable, reusable, and verifiable. To realize this specification, AssemCAD introduces a port- and mate-based CAD assembly library that executes symbolic assembly relations through deterministic mate transformations and validates declared interfaces using concrete B-Rep geometric evidence. Built on this representation and library, AssemCAD further supports on-demand synthesis of reusable parametric component factories for both standard and open-world geometries. Experiments on AssemBench show that AssemCAD substantially improves assembly preservation and physical validity over code-centric CAD generation baselines, while generalizing across different foundation-model backbones. By combining axiom-grounded assembly reasoning with deterministic geometric execution, AssemCAD extends Text-to-CAD from isolated part generation toward production-ready mechanical assembly design.