Research

Paper

AI LLM February 19, 2026

El Agente Sólido: A New Age(nt) for Solid State Simulations

Authors

Sai Govind Hari Kumar, Yunheng Zou, Andrew Wang, Jesús Valdés-Hernández, Tsz Wai Ko, Nathan Yue, Olivia Leng, Hanyong Xu, Chris Crebolder, Alán Aspuru-Guzik, Varinia Bernales

Abstract

Quantum chemistry calculations are a key component of the materials discovery process. The results from first-principles explorations enable the prediction of material properties prior to experimental validation. Despite their impact, the practical use of first-principles methods remains limited by the expertise required to design, execute, and troubleshoot complex computational workflows. Even when workflows are successfully built, they are sometimes rigid and not adaptable to different use cases. Recent advances in large language models (LLMs) and agentic systems offer a pathway to flexibly automate these processes and lower barriers to entry. Here, we introduce El Agente Sólido, a hierarchical multi-agent framework for automating solid-state quantum chemistry workflows using the open-source Quantum ESPRESSO simulation package. The framework translates high-level scientific objectives expressed in natural language into end-to-end computational pipelines that include structure generation, input file construction, workflow execution, and post-processing analysis. El Agente Sólido integrates density functional theory with phonon calculations and machine-learning interatomic potentials to enable efficient and physically consistent simulations. Extensive benchmarking and case studies demonstrate that El Agente Sólido reliably executes a wide range of solid-state calculations, highlighting its potential to improve reproducibility and accelerate computational materials discovery

Metadata

arXiv ID: 2602.17886
Provider: ARXIV
Primary Category: cond-mat.mtrl-sci
Published: 2026-02-19
Fetched: 2026-02-23 05:33

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.17886v1</id>\n    <title>El Agente Sólido: A New Age(nt) for Solid State Simulations</title>\n    <updated>2026-02-19T22:46:26Z</updated>\n    <link href='https://arxiv.org/abs/2602.17886v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.17886v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Quantum chemistry calculations are a key component of the materials discovery process. The results from first-principles explorations enable the prediction of material properties prior to experimental validation. Despite their impact, the practical use of first-principles methods remains limited by the expertise required to design, execute, and troubleshoot complex computational workflows. Even when workflows are successfully built, they are sometimes rigid and not adaptable to different use cases. Recent advances in large language models (LLMs) and agentic systems offer a pathway to flexibly automate these processes and lower barriers to entry. Here, we introduce El Agente Sólido, a hierarchical multi-agent framework for automating solid-state quantum chemistry workflows using the open-source Quantum ESPRESSO simulation package. The framework translates high-level scientific objectives expressed in natural language into end-to-end computational pipelines that include structure generation, input file construction, workflow execution, and post-processing analysis. El Agente Sólido integrates density functional theory with phonon calculations and machine-learning interatomic potentials to enable efficient and physically consistent simulations. Extensive benchmarking and case studies demonstrate that El Agente Sólido reliably executes a wide range of solid-state calculations, highlighting its potential to improve reproducibility and accelerate computational materials discovery</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cond-mat.mtrl-sci'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='physics.chem-ph'/>\n    <published>2026-02-19T22:46:26Z</published>\n    <arxiv:comment>42 pages, 31 figures, 18 tables</arxiv:comment>\n    <arxiv:primary_category term='cond-mat.mtrl-sci'/>\n    <author>\n      <name>Sai Govind Hari Kumar</name>\n    </author>\n    <author>\n      <name>Yunheng Zou</name>\n    </author>\n    <author>\n      <name>Andrew Wang</name>\n    </author>\n    <author>\n      <name>Jesús Valdés-Hernández</name>\n    </author>\n    <author>\n      <name>Tsz Wai Ko</name>\n    </author>\n    <author>\n      <name>Nathan Yue</name>\n    </author>\n    <author>\n      <name>Olivia Leng</name>\n    </author>\n    <author>\n      <name>Hanyong Xu</name>\n    </author>\n    <author>\n      <name>Chris Crebolder</name>\n    </author>\n    <author>\n      <name>Alán Aspuru-Guzik</name>\n    </author>\n    <author>\n      <name>Varinia Bernales</name>\n    </author>\n  </entry>"
}