Awesome AI4CAD Hub Papers · Datasets · Projects
← Back to papers

Automated CAD Modeling Sequence Generation from Text Descriptions via Transformer-Based Large Language Models

arXiv 2025 55 method, application

TLDR

A framework integrating LLMs with a Transformer-based generator to automate CAD model creation from text descriptions.

Reasoning

The paper presents a novel approach combining LLMs and a Transformer-based CAD generator for text-to-CAD, with a semi-automated annotation pipeline. Strengths include clear innovations and reported performance gains, but the abstract lacks details on real-world benchmarks and limitations.

Read-first score

Read-first score 55, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 72.

Recency 8%
86.7

Uses a gentle age decay so recent papers surface without erasing older foundations. 2025

Methodology quality 25%
70

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=experiment,metric,result

Reproducibility 25%
46

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=code,github

Topical relevance 42%
45

Uses existing LLM keyword relevance scores normalized to 0-100. AI for CAD,computer-aided design,neural CAD,generative CAD,parametric CAD,B-Rep,boundary representation,constructive solid geometry,CSG,sketch extrusion,CAD generation,CAD reconstruction,text-to-CAD,image-to-CAD,point cloud to CAD,CAD program

Field roles

FrontierMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 9.

Keyword Scores

computer-aided design
10
CAD generation
10
text-to-CAD
10
AI for CAD
9
generative CAD
9
CAD program
8
neural CAD
7
parametric CAD
6
CAD reconstruction
3
B-Rep
0
boundary representation
0
constructive solid geometry
0
CSG
0
sketch extrusion
0
image-to-CAD
0
point cloud to CAD
0

Deep Analysis

Innovations

  • Semi-automated data annotation pipeline using LLMs and VLLMs to generate high-quality parameters and appearance descriptions
  • Transformer-based CAD generator (TCADGen) that predicts modeling sequences via dual-channel feature aggregation
  • CADLLM model that refines generated sequences by incorporating confidence scores from TCADGen

Methodology

A language-guided framework integrates large language models with computer-automated design. A semi-automated pipeline annotates data, then a Transformer-based generator (TCADGen) predicts CAD modeling sequences from text descriptions, and a refinement model (CADLLM) uses TCADGen's confidence scores to improve the sequences.

Key Results

The proposed approach outperforms traditional methods in both accuracy and efficiency for generating complex CAD models from textual prompts.

Tags