{
  "abstract": "Reliable use of thermophysical databases in exploratory chemistry requires resolving heterogeneous identifiers, reconciling experimental conditions, and preserving numerical provenance across large, nested records. We present a hierarchical large language model (LLM) agent framework, implemented with a custom ReAct reasoning engine, that translates naturallanguage research questions into traceable retrieval and analysis workflows over the NIST ThermoML database. The framework combines hierarchical canonical identifiers, queryconditioned evidence compaction, deterministic inspection ledgers and numerical-grounding gates, and tool-assisted Redlich–Kister fitting. Five case studies are discussed in detail, representing chemistry tasks spanning data-rich and data-sparse retrieval, binary-mixture correlation, and open-ended cosolvent screening. For an ethanol–water equimolar density query, the system reduced ~190k characters of search output to 2k and precisely recovered a measured density of 859.3 kg m-3 at an ethanol mole fraction of 0.498, 298.15 K, and 100 kPa. For methanolethanol viscosity, it selected condition-aligned mixture and pure-component records, examined the fitting results at different orders, and produced a 2nd-order Redlich–Kister fit with 𝑅 = 0.982. Results for an open-ended iron-electrodeposition electrolyte design query synthesized evidence from approximately 12k measurements across 200 data blocks. However, with numerical grounding disabled for this specific case, the answer contained severe numerical hallucinations despite qualitatively coherent reasoning. These cases establish the feasibility of agent-assisted ThermoML research and identify identity management, evidence compaction, and deterministic numerical provenance as central design requirements for reliable chemistry-database research agents with some level of abstraction chemistry reasoning.",
  "abstract_shown": true,
  "affiliations": [
    "Center for Steel Electrification by Electrosynthesis",
    "Argonne National Laboratory",
    "Chemical Sciences and Engineering Division",
    "Physics Division",
    "Materials Science Division"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "affs": [
        0,
        1,
        2
      ],
      "name": "Yunkai Sun",
      "orcid": "0000-0001-8044-4936"
    },
    {
      "affs": [
        3,
        1
      ],
      "name": "Adwaith Ravichandran"
    },
    {
      "affs": [
        0,
        1,
        4
      ],
      "name": "Hassan Harb"
    },
    {
      "affs": [
        0,
        1,
        4
      ],
      "name": "Rajeev S. Assary"
    },
    {
      "affs": [
        0,
        1,
        2
      ],
      "name": "Brian J. Ingram"
    },
    {
      "affs": [
        0,
        1,
        2
      ],
      "name": "Zhenzhen Yang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/31dg4s8mppy88.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15009028/v1",
  "fulltext_url": null,
  "id": "31dg4s8mppy88",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009028/v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7212155694",
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-17",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/31dg4s8mppy88.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:19Z",
      "native_id": "10.26434/chemrxiv.15009028",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009028/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "A traceable agentic framework for chemistry research query and analysis with ThermoML database",
  "title_text": "A traceable agentic framework for chemistry research query and analysis with ThermoML database",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:19Z",
  "url": "https://research.draconitic.com/paper/31dg4s8mppy88",
  "venue": "ChemRxiv",
  "versions": []
}