{
  "abstract": "We present an LLM-assisted framework for microscopic transport studies that connects a general-purpose large language model (LLM) to the UrQMD transport model through a model-specific Skill and a deterministic scientific tool layer. The LLM supports literature-guided scientific planning and interpretation, while numerical calculations, event-history reconstruction, and statistical analyses are performed by deterministic tools. As a demonstration, the framework is applied to proton azimuthal-partition fluctuations in Au+Au collisions at $\\sqrt{s_{NN}}=3.0$--39~GeV. In the 0--5\\% centrality class, the fluctuations are statistically resolved below zero from 3 to 27~GeV and consistent with zero at 39~GeV. An exact pair-kernel decomposition shows that the negative signal is carried mainly by proton pairs containing at least one decay-fed proton. A random-label null test further distinguishes the observed pair contributions from expectations based on pair abundance alone. Reaction-history tracing shows that, for pairs of two decay-fed protons, the negative pair-kernel contribution is already present in the parent momenta evaluated at their respective formation vertices. The modular architecture is designed to accommodate different general-purpose LLMs and can be extended to other microscopic transport models through dedicated Skills and tool interfaces. This provides a pathway toward systematic microscopic analyses and comparisons across transport models within a common LLM-assisted framework.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.30198",
  "author_total": 2,
  "authors": [
    {
      "name": "Fu-Peng Li"
    },
    {
      "name": "Yige Huang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/8kdhb1247r4rm.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.30198",
  "fulltext_url": null,
  "id": "8kdhb1247r4rm",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.30198",
  "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",
      "nucl-th"
    ],
    [
      "openalex",
      "3106|High-Energy Particle Collisions Research"
    ]
  ],
  "openalex": "W7223351963",
  "pdf_url": "https://arxiv.org/pdf/2610.30198",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-21",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/8kdhb1247r4rm.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:34:34Z",
      "native_id": "2610.30198",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.30198"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:nucl-th",
      "subfield": "nuclear"
    }
  ],
  "title": "UrQMD-Agent: An LLM-Assisted Framework for Microscopic Tracing of Proton Azimuthal Correlations",
  "title_text": "UrQMD-Agent: An LLM-Assisted Framework for Microscopic Tracing of Proton Azimuthal Correlations",
  "type": "preprint",
  "updated_at": "2026-10-30T12:34:34Z",
  "url": "https://research.draconitic.com/paper/8kdhb1247r4rm",
  "venue": "arXiv",
  "versions": []
}