{
  "abstract": "Artificial intelligence is reshaping scientific exploration, but most methods automate procedural tasks without engaging in scientific reasoning, limiting autonomy in discovery. We demonstrate that hierarchical agentic large language model reasoning can efficiently drive simulation and scientific exploration. Across two chemical applications, CO adsorption on Cu surface transition metal adatoms and on M–N–C catalysts, reasoning-guided exploration reduces required atomistic simulations by up to 90% relative to heuristic or random selection. Comparisons across single-agent, multi-agent, and stochastic baselines show that hierarchical strategies yield more coherent and information-efficient search trajectories. Reasoning traces reveal chemically grounded decisions that cannot be explained by semantic bias or stochastic sampling. We realize these agentic reasoning strategies in Materials Agents for Simulation and Theory in Electronic-structure Reasoning (MASTER), a multimodal system that translates natural language into density functional theory workflows. Altogether, multi-agent collaboration accelerates heterogeneous catalyst discovery and marks a step toward more autonomous, reasoning-guided scientific exploration.",
  "abstract_shown": true,
  "affiliations": [
    "School of Civil & Environmental Engineering, University of Connecticut, Storrs, CT, USA",
    "Theoretical Division, Los Alamos National Laboratory, Los Alamos, NM, USA"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Samuel Rothfarb",
      "orcid": "0009-0004-6696-9495"
    },
    {
      "affs": [
        1
      ],
      "name": "Megan Christina Davis",
      "orcid": "0000-0002-4038-8615"
    },
    {
      "affs": [
        1
      ],
      "name": "Ivana Matanović"
    },
    {
      "affs": [
        0
      ],
      "name": "Baikun Li"
    },
    {
      "affs": [
        1
      ],
      "name": "Edward F. Holby",
      "orcid": "0000-0001-8419-6298"
    },
    {
      "affs": [
        1
      ],
      "name": "Wilton J. M. Kort-Kamp",
      "orcid": "0000-0002-0679-6690"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/fe2gny6j3w5mp.bib",
  "cited_by": 14,
  "doi": "10.1038/s41524-026-02139-1",
  "fulltext_url": null,
  "id": "fe2gny6j3w5mp",
  "issns": [
    "2057-3960"
  ],
  "landing_url": "https://doi.org/10.1038/s41524-026-02139-1",
  "language": "en",
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7162333481",
  "pdf_url": "https://www.nature.com/articles/s41524-026-02139-1_reference.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-05-25",
  "publisher": "Nature Portfolio",
  "ris": "https://research.draconitic.com/paper/fe2gny6j3w5mp.ris",
  "sources": [
    {
      "first_seen": "2026-11-04T13:21:19Z",
      "native_id": "W7162333481",
      "source": "openalex",
      "url": "https://doi.org/10.1038/s41524-026-02139-1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "Hierarchical Multi-agent Large Language Model Reasoning for Autonomous Heterogeneous Catalyst Discovery",
  "title_text": "Hierarchical Multi-agent Large Language Model Reasoning for Autonomous Heterogeneous Catalyst Discovery",
  "type": "peer-reviewed",
  "updated_at": "2026-11-08T13:20:56Z",
  "url": "https://research.draconitic.com/paper/fe2gny6j3w5mp",
  "venue": "npj Computational Materials",
  "versions": []
}