{
  "abstract": "Scientific code generation can produce executable programs that fail to compute the intended scientific object. We study this problem in language-model synthesis of Clifford circuits, which prepare the stabilizer states used in quantum error correction and admit exact classical verification. In our target-conditioned framework, each target is given as compact signed stabilizer generators, and an exact verifier checks the generated OpenQASM circuits. We supervise models with Aaronson-Gottesman chain-of-thought (AG-CoT) traces checked by the verifier, and continue training on model generations that the verifier accepts. Across two independently trained model families (3B and 7B), AG-CoT supervision multiplies greedy-decode state-equivalence accuracy by four to six times over circuit-only baselines, and verifier-filtered continuation training adds a further consistent gain atop both. A complementary 32B study shows that supervised models achieve near-perfect syntax and Clifford validity while the strongest direct model reaches 6.14% state equivalence per target, rising to over 10% under verifier-guided selection with multiple candidates. These results show that algorithmic trace supervision gives a large, statistically significant gain in both model families and that verifier-filtered continuation adds a further repeated gain. The persistent gap between Clifford validity and state equivalence confirms that exact verification is necessary: a circuit can be syntactically and physically valid yet prepare the wrong quantum state.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.33192",
  "author_total": 5,
  "authors": [
    {
      "name": "Lu Wei"
    },
    {
      "name": "Yufeng Wang"
    },
    {
      "name": "Chenfeng Cao"
    },
    {
      "name": "Lu Pang"
    },
    {
      "name": "Haibin Ling"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3xb8wg2za00fg.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.33192",
  "fulltext_url": null,
  "id": "3xb8wg2za00fg",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.33192",
  "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",
      "cs.CL"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "quant-ph"
    ],
    [
      "openalex",
      "1702|Quantum Computing Algorithms and Architecture"
    ]
  ],
  "openalex": "W7214716140",
  "pdf_url": "https://arxiv.org/pdf/2609.33192",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-27",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/3xb8wg2za00fg.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:12Z",
      "native_id": "2609.33192",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.33192"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:quant-ph",
      "subfield": "quantum"
    }
  ],
  "title": "AG-CoT: Verified Algorithmic Traces for LLM Program Synthesis on Clifford Circuits",
  "title_text": "AG-CoT: Verified Algorithmic Traces for LLM Program Synthesis on Clifford Circuits",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:12Z",
  "url": "https://research.draconitic.com/paper/3xb8wg2za00fg",
  "venue": "arXiv",
  "versions": []
}