Case Studies of Materials Agents
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
This chapter presents an in-depth analysis of autonomous discovery in materials science, comparing autonomous agents with traditional methods in terms of efficiency, accuracy, and scalability. The case study of AtomAgents, a multi-agent system for alloy design and discovery, is explored. AtomAgents integrates large language models (LLMs) with knowledge retrieval, multimodal data integration, and physics-based simulations to automate alloy design. The system's architecture consists of three core modules: brain (decision-making), perception (data processing), and action (task execution). AtomAgents demonstrates proficiency in material property calculations and defect analysis, enabling autonomous design of alloys with superior properties. The chapter details the system's architecture, experimental design, and verification, highlighting its transformative potential in materials science.
Fields of Study & Subjects
Machine Learning in Materials Science
Artificial Intelligence Applications
Material Selection and Properties
Publication details
- Journal / source
- Wiley eBooks
- Pages
- 505–550
- Publication date
- 17 March 2026
- Language
- EN
- Document type
- Book chapter