{
  "abstract": "This study evaluates a protocol-guided large language model (LLM) agent workflow for quantum program synthesis and execution. A versioned YAML protocol specifies interface and quantum-semantic requirements while leaving circuit design to the model. The workflow combines Qiskit circuit generation, evaluator-guided repair, and quantum processing unit (QPU) deployment. A matched ablation evaluates four LLM endpoints using the variational quantum eigensolver (VQE) for H$_2$, the quantum approximate optimization algorithm (QAOA) for MaxCut, and Fashion-MNIST quantum-kernel classification. Across 240 trials, protocol guidance increased evaluator completion from 80.0\\% to 99.2\\%, reduced mean repairs from 2.56 to 0.75, and reduced mean agent time from 55.70 to 30.58~s. Provider-reported token use decreased for three of four endpoints. Completed VQE trials meeting chemical accuracy increased from 16/40 to 29/40, while valid QAOA approximation ratios remained comparable. Semantic review identified rank-one fidelity kernels, reinforcing the distinction between evaluator completion and semantic validity. A 210-run IBM QPU study evaluated the combined generation-and-selection pipelines and confirmed deployment feasibility. The results support protocol guidance as a software-reliability layer that must be complemented by quantum-semantic validation.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.20258",
  "author_total": 2,
  "authors": [
    {
      "name": "Ming-Kang Ho"
    },
    {
      "name": "Tai-Yue Li"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9smermtjqnmcc.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.20258",
  "fulltext_url": null,
  "id": "9smermtjqnmcc",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.20258",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "quant-ph"
    ],
    [
      "openalex",
      "1702|Quantum Computing Algorithms and Architecture"
    ]
  ],
  "openalex": "W7213590431",
  "pdf_url": "https://arxiv.org/pdf/2609.20258",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/9smermtjqnmcc.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:22:19Z",
      "native_id": "2609.20258",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.20258"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:quant-ph",
      "subfield": "quantum"
    }
  ],
  "title": "A Protocol-Guided LLM Agent for Quantum Program Synthesis and Execution",
  "title_text": "A Protocol-Guided LLM Agent for Quantum Program Synthesis and Execution",
  "type": "preprint",
  "updated_at": "2026-10-30T12:22:19Z",
  "url": "https://research.draconitic.com/paper/9smermtjqnmcc",
  "venue": "arXiv",
  "versions": []
}