Material selection is fundamental to the design process, as it significantly impacts a product’s cost, performance, appearance, manufacturability, and sustainability. It is a complex, open-ended challenge that forces designers to continuously adapt to new information, balance diverse stakeholder demands, weigh trade-offs, and navigate uncertainties to achieve the optimal outcome. 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. However, discrepancies between LLM outputs and expert recommendations indicate the need for further research. To address the limitations of standalone LLMs, particularly their lack of reasoning and action-execution capabilities, agentic AI has been developed with enhanced functionalities. These agents, which maintain access to LLMs, are equipped with tools and the ability to interact with external environments, enabling them to retrieve and analyze information, reason through complex scenarios, and refine their outputs through iterative feedback. This study examines how LLMs, augmented with advanced search tools, can more effectively emulate expert decision-making in material selection. Our findings reveal a non-linear relationship between model size and performance, with some larger models demonstrating lower proximity to human survey results and struggling to follow instructions. These insights contribute to the broader understanding of AI integration in design workflows.
📦 Agents-for-Material-Selection
├─ Data # Data collected
├─ Data Evaluation # Scripts used to evaluate the results
├─ Data Generation # Scripts used to generate the results
├─ Search Logs # Search logs collected
├─ Search Logs Data # Data generated to evaluate search logs
└─ Search Logs Evaluation # Scripts used to evaluate the search logs