{
  "abstract": "Inverse design of dielectric metasurfaces is powerful but labour-intensive: each new target requires choosing a parameterization and a figure of merit, managing compute resources, and critically assessing results that may be numerically unconverged, sensitive to fabrication errors or trapped in local optima. Here we present an open-source pipeline in which an artificial intelligence (AI) coding agent turns a plain-language specification into metasurface optimization runs, executes them, analyses every run with a fixed checklist and proposes the next iteration. Designs are optimized with differentiable three-dimensional rigorous coupled-wave analysis (RCWA), including robustness to fabrication tolerances, and every reported design is independently verified with finite-difference time-domain (FDTD) simulations. We demonstrate the workflow at 1550 nm on a freeform silicon metagrating, on a polarization-independent meta-atom library assembled into beam-deflecting supercells, and on metalenses built from the same library. In the metagrating case, the independent FDTD verification revealed a 5\\% overestimate of the efficiency by the optimization model that a conventional convergence test had not detected, and the robust design retained most of its efficiency under $\\pm$10~nm fabrication errors. In the other cases, instead, the obtained RCWA results are confirmed by full-wave simulations.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2611.08127",
  "author_total": 5,
  "authors": [
    {
      "name": "Giuseppe Emanuele Lio"
    },
    {
      "name": "Roberto Caputo"
    },
    {
      "name": "Alain J. Corso"
    },
    {
      "name": "Maria Guglielmina Pelizzo"
    },
    {
      "name": "Antonio Ferraro"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0h7fbvjzn9ffh.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2611.08127",
  "fulltext_url": null,
  "id": "0h7fbvjzn9ffh",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2611.08127",
  "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",
      "physics.optics"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2611.08127",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-05",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0h7fbvjzn9ffh.ris",
  "sources": [
    {
      "first_seen": "2026-11-06T18:21:30Z",
      "native_id": "2611.08127",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2611.08127"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.optics",
      "subfield": "optics-photonics"
    }
  ],
  "title": "An Agent-Driven, Cross-Validated Inverse-Design Pipeline for Dielectric Metasurfaces",
  "title_text": "An Agent-Driven, Cross-Validated Inverse-Design Pipeline for Dielectric Metasurfaces",
  "type": "preprint",
  "updated_at": "2026-11-09T00:20:41Z",
  "url": "https://research.draconitic.com/paper/0h7fbvjzn9ffh",
  "venue": "arXiv",
  "versions": []
}