Agentic AI framework explores grain boundary behavior in metals
GBClaw: An agentic AI framework for atomistic grain boundary research and mechanistic discovery
Artificial IntelligenceMultiagent Systems
Summary
Materials like metals are made of tiny crystals joined at interfaces called grain boundaries, which affect how strong and durable the material is. Studying these boundaries is hard because their structures are complicated. The authors created GBClaw, a computer system that uses AI to run simulations and analyze these boundaries automatically. By testing GBClaw on nickel, they found how defects in the boundaries influence how the material bends and slides, helping to explain what makes some boundaries stronger than others.
What this means in practice
- •For materials engineers: Simulate and analyze how different grain boundary defects alter metal deformation to design stronger alloys.
- •For computational physicists: Use an AI-guided framework to integrate simulation and mechanistic insights for studying complex interfaces efficiently.
- •For automotive manufacturers: Incorporate AI-powered grain boundary analysis into quality control workflows to predict and improve metal part performance.$Commercial implications: Enables selling advanced predictive tools for metal durability assessment tailored to automotive suppliers.
Authors
Yazhuo Liu, Kunqing Ding, Xiaoguo Gong, Zifeng Wang, Yichen Yang, Yifeng Che, Wen Chen, Josh Kacher, Olivier Pierron, Shigenobu Ogata, Ting Zhu
Abstract
Agentic artificial intelligence (AI) systems hold immense potential for automating complex workflows in materials discovery and design, but extending them to domain-intensive mechanistic investigations remains challenging. Here, we present GBClaw, an agentic AI framework for investigating the structure and deformation of general grain boundaries (GBs). Although general GBs constitute the vast majority of real-world interfaces in polycrystalline materials, they remain understudied because their structural complexity and interfacial mismatch complicate experimental and modeling research. GBClaw integrates large language models (LLMs) into a modular architecture comprising an orchestrator, specialized agents, domain-specific tools, simulation interfaces, and hierarchical memory. Through dynamic replanning and iterative workflow refinement, the framework effectively connects systematic simulations with targeted mechanistic analysis. Applied to 14 general asymmetric tilt GBs in nickel, GBClaw characterized interfacial defect structures and identified diverse deformation modes across these incommensurate boundaries. Comparing boundary sliding with and without secondary GB misfit dislocations revealed substantial differences in shear strength, underscoring the critical role of defect hierarchies in sliding resistance. Furthermore, researcher-guided follow-up calculations traced an anomalously high shear resistance to metastable boundary structures. This work demonstrates that combining agentic AI with domain expertise bridges high-throughput computational screening with deep physical understanding of complex material interfaces.