Recently Published by Autodesk Researchers

Autodesk Research teams regularly contribute to peer-reviewed scientific journals and present at conferences around the world. Check out some recent publications from Autodesk Researchers.

Evaluating the Role of Model Size in Agentic AI for Expert-Like Material Selection

Material selection is fundamental to the design process, as it significantly affects the cost, performance, appearance, manufacturability, and sustainability of a product. Previous studies have explored the potential of large language models (LLMs) to assist in the material selection process, with findings suggesting that LLMs could provide valuable support. This study compares standalone LLMs and agentic AI frameworks, examining how search-augmented agents can more effectively emulate expert decision-making in material selection.

A Domain Adaptation of Large Language Models for Classifying Mechanical Assembly Components

The conceptual design phase represents a critical early stage in the product development process, where designers generate potential solutions that meet predefined design specifications based on functional requirements. This study proposes a novel LLM-based domain adaptation framework using fine-tuning for the automated classification of mechanical assembly parts’ functions. By fine-tuning LLMs on domain-specific datasets, the traditionally manual and subjective process of function annotation can be improved in both accuracy and consistency.

MSEval: A Dataset for Material Selection in Conceptual Design to Evaluate Algorithmic Models

Material selection plays a pivotal role in many industries, from manufacturing to construction. In design research, material selection is frequently modeled as a structured decision-making process, where optimization techniques, whether single- or multi-objective, are employed to identify solutions that best meet the design requirements. This article presents MSEval, a novel dataset comprised expert material evaluations across a variety of design briefs and criteria. This dataset is designed to serve as a benchmark to facilitate the evaluation and modification of machine learning models in the context of material selection for conceptual design. By focusing on a diverse set of design tasks and criteria, MSEval enables a more nuanced understanding of the material selection and the thought process, providing valuable insights for both human designers and AI systems.