{
  "abstract": "Data-driven materials discovery interpolates more reliably than it extrapolates and seldom reveals new structure types. We present MatEvolve, an agentic-AI framework that designs crystals in an interpretable \\emph{language of motifs}, in which each crystal is written as a \\emph{motif profile} that describes the recurring geometric patterns---the \\emph{motifs}---composing the crystal. The motif profile serves not merely as a description of a material but as the medium for material design: the agent edits the profile with a stated rationale and constructs a crystal from the modified one; the most promising candidates are then validated by first-principles calculations. MatEvolve is built on the state-of-the-art language model Claude Fable~5 without fine-tuning. It is applied to the design of rare-earth-lean permanent-magnet compounds and finds novel (meta)stable crystals that are both new structural prototypes and magnet compounds; under an equal validation budget, it does so an order of magnitude more often than generative models. Beyond design, analyzing the human-readable profiles of the discovered crystals reveals their structure--property relationships.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2608.15900",
  "author_total": 9,
  "authors": [
    {
      "name": "Dinh-Khiet Le"
    },
    {
      "name": "Minh-Quyet Ha"
    },
    {
      "name": "Hong-Phuc Vu-Dinh"
    },
    {
      "name": "Viet-Cuong Nguyen"
    },
    {
      "name": "Huan Tran"
    },
    {
      "name": "Truyen Tran"
    },
    {
      "name": "Takashi Miyake"
    },
    {
      "name": "Hiori Kino"
    },
    {
      "name": "Hieu-Chi Dam"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/a5tz2xsfne9tk.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2608.15900",
  "fulltext_url": null,
  "id": "a5tz2xsfne9tk",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2608.15900",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cond-mat.mtrl-sci"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "openalex",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7203725837",
  "pdf_url": "https://arxiv.org/pdf/2608.15900",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-21",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/a5tz2xsfne9tk.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:34:18Z",
      "native_id": "2608.15900",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2608.15900"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:cond-mat.mtrl-sci",
      "subfield": "condensed-matter"
    }
  ],
  "title": "Crystal-structure design by agentic AI in a language of motifs",
  "title_text": "Crystal-structure design by agentic AI in a language of motifs",
  "type": "preprint",
  "updated_at": "2026-10-30T12:34:18Z",
  "url": "https://research.draconitic.com/paper/a5tz2xsfne9tk",
  "venue": "arXiv",
  "versions": []
}