{
  "abstract": "Chemistry has recently entered a high-data regime as molecular databases from highthroughput platforms or computational studies have become available. Increasing automation within the chemical sciences leads to a more digital and precision chemistry. Dedicated scientific agents are becoming central to guiding the chemist through an ever-increasing amount of data and findings, including negative ones. Here, we introduce Magnolia, a persistent-memory artificial intelligence agent framework that integrates computational protocols, from docking to quantum chemistry, lab notebooks and chat logs relying on large language models (LLMs). It relies on a three-tier memory system: session-level observations are automatically captured and distilled into structured learnings, confirmed and elevated to project-tier entries and, when human-validated, promoted to cross-project rules that actively guide subsequent work and provide direct chemical feedback. We illustrate Magnolia on four case studies: quantum-chemical evaluation of aromatic systems (COMPAS database), molecular dynamics of butane and of modified DNA, and a protein–peptide docking campaign. Across these projects, Magnolia tracked 317 runs and accumulated 116 project-tier entries, from which four cross-project rules were promoted; in controlled replays of four tasks, runs with memory passed the checks that runs without it failed (for example, ten of ten docking-configuration checks, against one to four of ten). By combining automation, reproducibility, and human-in-the-loop control, our Magnolia framework streamlines docking, molecular dynamics and quantum chemistry calculations with direct analysis and LLM-augmented feedback, offering accelerated access to computational (bio)chemistry.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.27230",
  "author_total": 6,
  "authors": [
    {
      "name": "Tao Jiang"
    },
    {
      "name": "Benjamin Navet"
    },
    {
      "name": "Yousouf Taghzouti"
    },
    {
      "name": "Fabien Gandon"
    },
    {
      "name": "Louis-Félix Nothias"
    },
    {
      "name": "Élise Dumont"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/37d1bf5qmeht8.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.27230",
  "fulltext_url": null,
  "id": "37d1bf5qmeht8",
  "issns": [],
  "landing_url": "https://univ-cotedazur.hal.science/hal-05830611v1",
  "language": "en",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "q-bio.BM"
    ],
    [
      "hal",
      "0.chim"
    ],
    [
      "hal",
      "0.info"
    ],
    [
      "openalex",
      "1802|Scientific Computing and Data Management"
    ]
  ],
  "openalex": "W7223086517",
  "pdf_url": "https://univ-cotedazur.hal.science/hal-05830611/document",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-19",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/37d1bf5qmeht8.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:00Z",
      "native_id": "hal-05830611",
      "source": "hal",
      "url": "https://univ-cotedazur.hal.science/hal-05830611v1"
    },
    {
      "first_seen": "2026-10-30T12:34:08Z",
      "native_id": "2610.27230",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.27230"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "arxiv:q-bio.BM",
      "subfield": "biophysics"
    },
    {
      "field": "chemistry",
      "origin": "hal:0.chim",
      "subfield": "general"
    }
  ],
  "title": "Magnolia: A Persistent-Memory Agent Framework for Computational Chemistry",
  "title_text": "Magnolia: A Persistent-Memory Agent Framework for Computational Chemistry",
  "type": "preprint",
  "updated_at": "2026-10-30T12:34:08Z",
  "url": "https://research.draconitic.com/paper/37d1bf5qmeht8",
  "venue": "HAL",
  "versions": []
}