{
  "abstract": "First-principles calculations are rarely single solver calls: they are multistage workflows in which structures, settings, and saved densities must pass correctly between dependent stages. Language models can write a valid single input, but reliability collapses once stages are chained: a dropped dependency, wrong file handoff, or hallucinated keyword can invalidate results even when the solver runs, and such errors surface only after costly execution. We introduce LatticeMind, a validation-gated agentic framework that converts natural-language requests into executable, checkable density functional theory (DFT) projects. A workflow contract specifies required stages, files, and dependencies; deterministic validators inspect the project before any solver launch; failed checks trigger bounded repair; and reports remain traceable to project files. On a 44-case RESCU benchmark spanning total-energy, density-of-states, band-structure, magnetic, phonon workflows, three non-flagship LLM backends reproduced every reference value; 119 of 132 runs passed on the first validated plan and the rest after one repair cycle. Ablations identify the workflow contract and pre-execution validation as the principal reliability mechanisms; a conventional trial-and-repair baseline reaches 71% at twice the token cost per success. The same architecture reproduces every reference value on a 19-case VASP benchmark, demonstrating transfer across solvers. Beyond these task families, LatticeMind generated and validated the 23 inputs of a multistage study of Rh-induced electronic responses at a Rh$_6$/In$_x$Ga$_{1-x}$N photocatalyst interface. These results establish workflow contracts, deterministic validation, bounded repair, and traceable records as a practical foundation for reliable AI-assisted scientific computing, where preventable errors are caught before execution and the solver is never the first validator.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.26869",
  "author_total": 6,
  "authors": [
    {
      "name": "Nathaniel M. Vegh"
    },
    {
      "name": "Yu Zhu"
    },
    {
      "name": "Raphaël J. Prentki"
    },
    {
      "name": "Félix Beaudoin"
    },
    {
      "name": "Shuaishuai Yuan"
    },
    {
      "name": "Hong Guo"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0fa4ts55368wc.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.26869",
  "fulltext_url": null,
  "id": "0fa4ts55368wc",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.26869",
  "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"
    ],
    [
      "arxiv",
      "physics.comp-ph"
    ],
    [
      "arxiv",
      "quant-ph"
    ],
    [
      "openalex",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7223094151",
  "pdf_url": "https://arxiv.org/pdf/2610.26869",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0fa4ts55368wc.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:34:04Z",
      "native_id": "2610.26869",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.26869"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.comp-ph",
      "subfield": "computational"
    },
    {
      "field": "physics",
      "origin": "arxiv:cond-mat.mtrl-sci",
      "subfield": "condensed-matter"
    },
    {
      "field": "physics",
      "origin": "arxiv:quant-ph",
      "subfield": "quantum"
    }
  ],
  "title": "LatticeMind: A Validation-Gated Agentic Framework for Density Functional Theory Workflows",
  "title_text": "LatticeMind: A Validation-Gated Agentic Framework for Density Functional Theory Workflows",
  "type": "preprint",
  "updated_at": "2026-10-30T12:34:04Z",
  "url": "https://research.draconitic.com/paper/0fa4ts55368wc",
  "venue": "arXiv",
  "versions": []
}