CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solvers?

Shranjeno v:

Bibliografske podrobnosti
izdano v:	arXiv.org (Dec 18, 2024), p. n/a
Glavni avtor:	Mallis, Dimitrios
Drugi avtorji:	Karadeniz, Ahmet Serdar, Cavada, Sebastian, Rukhovich, Danila, Foteinopoulou, Niki, Cherenkova, Kseniya, Anis Kacem, Aouada, Djamila
Izdano:	Cornell University Library, arXiv.org
Teme:	Solvers Python Modules Computer aided design > CAD Large language models
Online dostop:	Citation/Abstract Full text outside of ProQuest
Oznake:	Označite Brez oznak, prvi označite!

Opis
Resumen:	We propose CAD-Assistant, a general-purpose CAD agent for AI-assisted design. Our approach is based on a powerful Vision and Large Language Model (VLLM) as a planner and a tool-augmentation paradigm using CAD-specific modules. CAD-Assistant addresses multimodal user queries by generating actions that are iteratively executed on a Python interpreter equipped with the FreeCAD software, accessed via its Python API. Our framework is able to assess the impact of generated CAD commands on geometry and adapts subsequent actions based on the evolving state of the CAD design. We consider a wide range of CAD-specific tools including Python libraries, modules of the FreeCAD Python API, helpful routines, rendering functions and other specialized modules. We evaluate our method on multiple CAD benchmarks and qualitatively demonstrate the potential of tool-augmented VLLMs as generic CAD task solvers across diverse CAD workflows.
ISSN:	2331-8422
Fuente:	Engineering Database