{
  "abstract": "Metasurface design increasingly requires fast models that can operate across structurally distinct device families, rather than retraining a separate surrogate for every geometry class. Conventional neural network surrogates often depend on fixed-dimensional descriptors, family-specific output formats, and repeated architecture tuning, which limits their scalability across heterogeneous meta-atoms. Here, we present a unified large language model (LLM) workflow for multi-family metasurface modeling and inverse-design. Geometries, design parameters, and optical response channels were converted into a shared instruction-following text format and used to fine-tune Gemma-2-9B across 8 metasurface families. Compared with single-family baselines, the joint model simultaneously predicted the optical responses of all metasurface families while reducing the MSE for each family by an average of 56.5%. The same representation was also used for inverse design. These results show that a shared sequence-based LLM interface can provide a practical route to cross-family metasurface design while reducing the need for task-specific surrogate architectures.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2608.26417",
  "author_total": 6,
  "authors": [
    {
      "name": "Huanshu Zhang"
    },
    {
      "name": "Lei Kang"
    },
    {
      "name": "Yuyan Chen"
    },
    {
      "name": "Luxiang Wang"
    },
    {
      "name": "Zhaolong Cao"
    },
    {
      "name": "Douglas H. Werner"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/1c08651n1q4vs.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2608.26417",
  "fulltext_url": null,
  "id": "1c08651n1q4vs",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2608.26417",
  "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",
      "cs.LG"
    ],
    [
      "arxiv",
      "physics.optics"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2608.26417",
  "pmcid": null,
  "pmid": null,
  "published": "2026-08-26",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/1c08651n1q4vs.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:00Z",
      "native_id": "2608.26417",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2608.26417"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.optics",
      "subfield": "optics-photonics"
    }
  ],
  "title": "Towards a universal meta-optics solver via large language models",
  "title_text": "Towards a universal meta-optics solver via large language models",
  "type": "preprint",
  "updated_at": "2026-10-30T12:18:00Z",
  "url": "https://research.draconitic.com/paper/1c08651n1q4vs",
  "venue": "arXiv",
  "versions": [
    {
      "doi": "10.1021/acs.nanolett.6c03323",
      "pid": "8w02fcjnbz7np",
      "relation": "published-as",
      "title": "Toward a Universal Meta-Optics Solver via Large Language Models.",
      "venue": "Nano letters"
    }
  ]
}