Newest papers

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

Yazhuo Liu, Kunqing Ding, Xiaoguo Gong, Zifeng Wang, Yichen Yang, Yifeng Che, Wen Chen, Josh Kacher, Olivier N. Pierron, Shigenobu Ogata, Ting Zhu · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28629 · cited by 0 works (OpenAlex) · open-access PDF

Portuguese

Este sistema de inteligência artificial agente (AI) tem um enorme potencial para automatizar fluxos de trabalho complexos na descoberta e design de materiais, mas estendê-los para investigações mecânicas intensivas de domínio permanece desafiador. Aqui, apresentamos o GBClaw, um complexo de inteligência artificial agente para investigar a estrutura e a deformação de limites gerais de grãos (GBs). Embora os GBs gerais constituam a grande maioria das interfaces do mundo real em materiais policristalinos, eles permanecem subestudados porque sua complexidade estrutural e desajuste interfacial resistem a pesquisas experimentais e de modelagem. O GBClaw integra modelos de linguagem de grande dimensão (MLLs) em uma arquitetura modular que inclui um orquestrador, agentes especializados, ferramentas

Machine translation (Meta M2M100); the English original follows.

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.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Workflow, Grain boundary, Modular design, Computer science, Domain (mathematical analysis), Deformation (meteorology)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange