{
  "abstract": "A frontier language model was recently reported to solve 1D NMR structural elucidation without tools. We ask whether this capability transfers to tandem mass spectrometry (MS/MS) in the de novo setting, where the model must propose a structure directly from the spectrum without a candidate list or reference library. To separate reasoning from recall, we build a 100-analyte benchmark from MassSpecGym, split by each analyte's textual footprint into in-distribution (well documented in literature) and out-of-distribution (essentially undocumented) arms. We hold the model, harness, and output format fixed and vary only the LLM's access to domain-specific tools. Without tools, a frontier LLM reaches 52% Top-1 accuracy in-distribution but only 2% out-of-distribution. Only access to de novo structure generators improves out-of-distribution accuracy, raising it to as much as 38% Top-1, and the resulting agent outperforms the standalone de novo models both in and out of distribution. These results suggest that LLMs are not effective at de novo MS/MS structural elucidation on their own, and that further gains depend on the specialist tools available to the agent rather than on the LLM itself.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2611.03308",
  "author_total": 6,
  "authors": [
    {
      "name": "Gabriel Asher"
    },
    {
      "name": "Cailum M. K. Stienstra"
    },
    {
      "name": "Tomo Oga"
    },
    {
      "name": "Devesh Shah Antonio H. de O. Fonseca"
    },
    {
      "name": "Niall O'Connor"
    },
    {
      "name": "Michael Widrich"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/70gxf8t1gfzf9.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2611.03308",
  "fulltext_url": null,
  "id": "70gxf8t1gfzf9",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2611.03308",
  "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.AI"
    ],
    [
      "arxiv",
      "cs.CL"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2611.03308",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-02",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/70gxf8t1gfzf9.ris",
  "sources": [
    {
      "first_seen": "2026-11-03T12:21:21Z",
      "native_id": "2611.03308",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2611.03308"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "LLMs Depend on Specialist Tools for Out-of-Distribution Generalization in MS/MS Structural Elucidation",
  "title_text": "LLMs Depend on Specialist Tools for Out-of-Distribution Generalization in MS/MS Structural Elucidation",
  "type": "preprint",
  "updated_at": "2026-11-05T15:20:35Z",
  "url": "https://research.draconitic.com/paper/70gxf8t1gfzf9",
  "venue": "arXiv",
  "versions": []
}