{
  "abstract": "Foundational machine-learning interatomic potentials (MLIPs) are transforming atomistic simulations by achieving near-ab initio accuracy across large chemical spaces at a fraction of the computational cost. A central challenge in using these tools for high-throughput property calculations is translating high-level scientific intent into adaptive simulation campaigns without compromising workflow rigour. We introduce El Agente Potente, an agentic system that combines typed execution graphs with a complementary coding mode for MLIPs-driven atomistic simulations. Typed execution graphs provide structured and provenance-aware execution for standardized workflows, with large language models (LLMs) restricted to planning and routing while deterministic Python components perform scientific computation and validation. Complementing this structured execution, a coding agent constructs customized workflows for tasks requiring greater procedural flexibility while invoking existing Potente functions for supported calculations. We demonstrate El Agente Potente across computational materials discovery, molecular energy-landscape exploration, adsorption, and catalytic reaction workflows, together with systematic benchmarks of reproducibility and LLM token cost. These results establish typed execution graphs and code-based workflow construction as complementary mechanisms for agentic scientific computing, combining controlled, auditable execution with the flexibility required for customized atomistic simulations",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.14840",
  "author_total": 9,
  "authors": [
    {
      "name": "Tsz Wai Ko"
    },
    {
      "name": "Jiaru Bai"
    },
    {
      "name": "Thomas Swanick"
    },
    {
      "name": "Yeonghun Kang"
    },
    {
      "name": "Changhyeok Choi"
    },
    {
      "name": "Angelina Qihong Jiang"
    },
    {
      "name": "Aiwei Yin"
    },
    {
      "name": "Varinia Bernales"
    },
    {
      "name": "Alán Aspuru-Guzik"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/fvd4g3catrf6r.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.14840",
  "fulltext_url": null,
  "id": "fvd4g3catrf6r",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.14840",
  "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.AI"
    ],
    [
      "arxiv",
      "physics.chem-ph"
    ],
    [
      "openalex",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7213325938",
  "pdf_url": "https://arxiv.org/pdf/2609.14840",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-13",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/fvd4g3catrf6r.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:25Z",
      "native_id": "2609.14840",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.14840"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "arxiv:physics.chem-ph",
      "subfield": "physical"
    }
  ],
  "title": "El Agente Potente: High-Throughput Agentic Atomistic Simulations",
  "title_text": "El Agente Potente: High-Throughput Agentic Atomistic Simulations",
  "type": "preprint",
  "updated_at": "2026-10-30T12:21:25Z",
  "url": "https://research.draconitic.com/paper/fvd4g3catrf6r",
  "venue": "arXiv",
  "versions": []
}