Mechanistic discovery in grain boundary structure and deformation driven by agentic AI
Abstract
Agentic artificial intelligence (AI) systems hold immense potential for automating complex workflows in materials discovery and design, but extending these capabilities to domain-intensive mechanistic studies remains challenging. General grain boundaries (GBs) exemplify this challenge, as their structural complexity complicates experimental characterization and atomistic modeling. Here, we present GBClaw, an agentic AI framework for investigating the structure and deformation of general GBs, which are common in real polycrystals yet remain understudied. By integrating large language models into a modular architecture, GBClaw effectively combines systematic simulations with targeted mechanistic analysis through iterative workflow refinement and dynamic replanning. Applied to 14 general asymmetric tilt GBs in nickel, the framework characterized interfacial defect structures and deformation modes across these incommensurate boundaries. It established a general approach to identify previously unobserved, widely spaced secondary GB misfit dislocations (SGBMDs) alongside closely spaced primary GB misfit dislocations (PGBMDs) in simulated atomic configurations and experimental images. Comparisons of GB sliding with and without SGBMDs revealed substantial differences in shear strength, underscoring the critical role of misfit-dislocation hierarchies in sliding resistance. Researcher-guided follow-up calculations further elucidated the structural origins of shear asymmetry and an anomalous shear response. This work demonstrates that combining agentic AI with domain expertise bridges high-throughput computational screening and deep mechanistic discovery at complex material interfaces.
Related
- Reducing boundary conditions for the Thomas–Fermi equation using a hybrid q-deformation and neural network method
- From Automated Simulation to Autonomous Discovery: A Hierarchical Framework for Agentic Computational Materials Science
- Automated Discovery of Physically Interpretable Subgrid Length Scales for Detached Eddy Simulation via Agentic AI
- Discovery of Interpretable Surrogates via Agentic AI: Application to Gravitational Waves
- Agentic Resource Allocation for Batch Multi-Objective Bayesian Optimization in Autonomous Materials Discovery
BibTeX
@misc{liu2026mechanistic,
title = {{Mechanistic discovery in grain boundary structure and deformation driven by agentic AI}},
author = {Yazhuo Liu and Kunqing Ding and Xiaoguo Gong and Zifeng Wang and Yichen Yang and Yifeng Che and Wen Chen and Josh Kacher and Olivier Pierron and Shigenobu Ogata and Ting Zhu},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.28629},
eprint = {2610.28629},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.28629},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Mechanistic discovery in grain boundary structure and deformation driven by agentic AI
AU - Yazhuo Liu
AU - Kunqing Ding
AU - Xiaoguo Gong
AU - Zifeng Wang
AU - Yichen Yang
AU - Yifeng Che
AU - Wen Chen
AU - Josh Kacher
AU - Olivier Pierron
AU - Shigenobu Ogata
AU - Ting Zhu
PY - 2026
DA - 2026/10/29
PB - arXiv
DO - 10.48550/arxiv.2610.28629
UR - https://arxiv.org/abs/2610.28629
AB - Agentic artificial intelligence (AI) systems hold immense potential for automating complex workflows in materials discovery and design, but extending these capabilities to domain-intensive mechanistic studies remains challenging. General grain boundaries (GBs) exemplify this challenge, as their structural complexity complicates experimental characterization and atomistic modeling. Here, we present GBClaw, an agentic AI framework for investigating the structure and deformation of general GBs, which are common in real polycrystals yet remain understudied. By integrating large language models into a modular architecture, GBClaw effectively combines systematic simulations with targeted mechanistic analysis through iterative workflow refinement and dynamic replanning. Applied to 14 general asymmetric tilt GBs in nickel, the framework characterized interfacial defect structures and deformation modes across these incommensurate boundaries. It established a general approach to identify previously unobserved, widely spaced secondary GB misfit dislocations (SGBMDs) alongside closely spaced primary GB misfit dislocations (PGBMDs) in simulated atomic configurations and experimental images. Comparisons of GB sliding with and without SGBMDs revealed substantial differences in shear strength, underscoring the critical role of misfit-dislocation hierarchies in sliding resistance. Researcher-guided follow-up calculations further elucidated the structural origins of shear asymmetry and an anomalous shear response. This work demonstrates that combining agentic AI with domain expertise bridges high-throughput computational screening and deep mechanistic discovery at complex material interfaces.
ER -