AI TrackerFrontier desk · AEST
Back to news
normalaitech

GBClaw: An agentic AI framework for atomistic grain boundary research and mechanistic discovery

arXiv cs.AI · 21 Oct 2026, 03:59 AEST

GBClaw is an agentic AI framework designed for atomistic grain boundary research and mechanistic discovery. It integrates large language models into a modular architecture to enhance the study of complex material interfaces.

Key facts

Read aloud

GBClaw is an agentic A I framework designed for atomistic grain boundary research and mechanistic discovery. It integrates large language models into a modular architecture to enhance the study of complex material interfaces. Agentic artificial intelligence A I systems hold immense potential for automating complex workflows in materials discovery and design, but extending them to domain-intensive mechanistic investigations remains challenging. GBClaw integrates large language models L L M s into a modular architecture comprising an orchestrator, specialized agents, domain-specific tools, simulation interfaces, and hierarchical memory. Applied to fourteen 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.

Sources in this cluster