{"slug": "gbclaw-an-agentic-ai-framework-for-atomistic-grain-boundary-research-and", "title": "GBClaw: An agentic AI framework for atomistic grain boundary research and mechanistic discovery", "summary": "A paper submitted to arXiv on 20 Oct 2026 presents GBClaw, an agentic AI framework that integrates large language models into a modular architecture of an orchestrator, specialized agents, domain-specific tools, simulation interfaces and hierarchical memory to investigate general grain boundaries in metals. Applied to 14 general asymmetric tilt grain boundaries in nickel, GBClaw characterized interfacial defect structures and identified diverse deformation modes, and comparisons of boundary sliding with and without secondary grain boundary misfit dislocations revealed substantial differences in shear strength. Researcher-guided follow-up calculations traced an anomalously high shear resistance to metastable boundary structures, which the authors say shows agentic AI combined with domain expertise can bridge high-throughput computational screening with physical understanding of complex material interfaces.", "body_md": "# Condensed Matter > Materials Science\n\n  [Submitted on 20 Oct 2026]\n\n# Title:GBClaw: An agentic AI framework for atomistic grain boundary research and mechanistic discovery\n\n[View PDF](http://arxiv.org/pdf/2610.28629v1)\n\nAbstract: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.\n    \n\n### Current browse context:\n\ncond-mat.mtrl-sci\n\n    Change to browse by:\n    \n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\nIArxiv Recommender\n\n*(*[What is IArxiv?](https://iarxiv.org/about))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/gbclaw-an-agentic-ai-framework-for-atomistic-grain-boundary-research-and", "canonical_source": "http://arxiv.org/abs/2610.28629v1", "published_at": "2026-10-21 14:32:51+00:00", "updated_at": "2026-10-21 15:10:54.536337+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-research", "large-language-models", "machine-learning"], "entities": ["GBClaw", "arXiv", "nickel"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/gbclaw-an-agentic-ai-framework-for-atomistic-grain-boundary-research-and", "markdown": "https://wpnews.pro/news/gbclaw-an-agentic-ai-framework-for-atomistic-grain-boundary-research-and.md", "text": "https://wpnews.pro/news/gbclaw-an-agentic-ai-framework-for-atomistic-grain-boundary-research-and.txt", "jsonld": "https://wpnews.pro/news/gbclaw-an-agentic-ai-framework-for-atomistic-grain-boundary-research-and.jsonld"}}