mlsanityData to 7 Oct 2026

From Idea to CAD: A Language Model-Driven Multi-Agent System for Collaborative Design

arXiv 2503.04417 ↗First posted 6 Mar 2025cs.AI cs.MAcited by 14

On the map: LLM agents and tool use → Multimodal and embodied agents

Abstract (arXiv)

Creating digital models using Computer Aided Design (CAD) is a process that requires in-depth expertise. In industrial product development, this process typically involves entire teams of engineers, spanning requirements engineering, CAD itself, and quality assurance. We present an approach that mirrors this team structure with a Vision Language Model (VLM)-based Multi Agent System, with access to parametric CAD tooling and tool documentation. Combining agents for requirements engineering, CAD engineering, and vision-based quality assurance, a model is generated automatically from sketches and/ or textual descriptions. The resulting model can be refined collaboratively in an iterative validation loop with the user. Our approach has the potential to increase the effectiveness of design processes, both for industry experts and for hobbyists who create models for 3D printing. We demonstrate the potential of the architecture at the example of various design tasks and provide several ablations that show the benefits of the architecture's individual components.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. Builds on 13 of its 23 references that are in the map. First posted on arXiv 6 Mar 2025.

Builds on

13 of 23 references.

References · 13

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  4. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  5. 2023ChatDev: Communicative Agents for Software Developmentcited by 893
  6. 2023Vision-Language Models for Vision Tasks: A Surveycited by 834
  7. 2023Text-to-image Diffusion Models in Generative AI: A Surveycited by 264
  8. 2024Generating CAD Code with Vision-Language Models for 3D Designscited by 61
  9. 2023From Concept to Manufacturing: Evaluating Vision-Language Models for Engineering Designcited by 51
  10. 2023CoPAL: Corrective Planning of Robot Actions with Large Language Modelscited by 39
  11. 2024OpenECAD: An Efficient Visual Language Model for Editable 3D-CAD Designcited by 26
  12. 2024Generative AI-based Prompt Evolution Engineering Design Optimization With Vision-Language Modelcited by 3
1 more
  1. 2024LLM2TEA: An Agentic AI Designer for Discovery with Generative Evolutionary Multitaskingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 9; 2026: 5.

14 papers.

Sort:

By area:

  1. 2025CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generationcited by 39
  2. 2025Seek-CAD: A Self-refined Generative Modeling for 3D Parametric CAD Using Local Inference via DeepSeekcited by 22
  3. 2025AI Agents in Engineering Design: A Multi-Agent Framework for Aesthetic and Aerodynamic Car Designcited by 20
  4. 2025Large Language Models for Computer-Aided Design: A Surveycited by 16
  5. 2026Text-to-CAD Evaluation with CADTestscited by 9
  6. 2025EvoCAD: Evolutionary CAD Code Generation with Vision Language Modelscited by 6
  7. 2025Toward Autonomous Engineering Design: A Knowledge-Guided Multi-Agent Frameworkcited by 5
  8. 2026Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Designcited by 3
  9. 2025Human-in-the-Loop: Quantitative Evaluation of 3D Models Generation by Large Language Modelscited by 2
  10. 2025GACO-CAD: Geometry-Augmented and Conciseness-Optimized CAD Model Generation from Single Imagecited by 2
  11. 2026CADIR: A Cross-Backend Editable Intermediate Representation for Agentic CAD Generationcited by 2
  12. 2025Helmsman: Autonomous Synthesis of Federated Learning Systems via Collaborative LLM Agentscited by 1
2 more
  1. 2026PLLM: Pseudo-Labeling Large Language Models for CAD Program Synthesiscited by 0
  2. 2026Memory-Augmented Reinforcement Learning Agent for CAD Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025CADDesigner: Conceptual CAD Model Generation with a General-Purpose Agent
  2. 2026Design-to-Plan: A Large Language Model-Based Multi-Agent Framework for Manufacturing Process Planning from 3D CAD Models and 2D Engineering Drawings
  3. 2026ArtisanCAD: An Industrial-Level CAD Agent with Expert-Grounded Knowledge Distillation
  4. 2025A Multidisciplinary Design and Optimization (MDO) Agent Driven by Large Language Models
  5. 2026LLM-Aided Design for Manufacturing: A Multi-Agent System for Intent-Preserving Redesign of CAD for Improved Manufacturability
  6. 2026ArtiCAD: Articulated CAD Assembly Design via Multi-Agent Code Generation
  7. 2026Zero-to-CAD: Agentic Synthesis of Interpretable CAD Programs at Million-Scale Without Real Data
  8. 2026TOOLCAD: Exploring Tool-Using Large Language Models in Text-to-CAD Generation with Reinforcement Learning