{
  "abstract": "Molecular generative models can rapidly explore chemical space, but conventional metrics alone do not establish whether proposed structures possess application-relevant physical properties. To address this limitation, we developed an integrated generationvalidation framework coupling Reversible Junction Tree Reinforcement Learning (RJT- RL) with automated density-functional tight-binding (DFTB) evaluation. Azobenzenebased molecular solar thermal fuels served as a representative case study. RJT-RL was guided by maximum Tanimoto similarity to a reference dataset, while reference and generated molecules were evaluated under identical DFTB calculation conditions to obtain the energy difference between the cis and trans isomers (∆ E iso ) and the S 0 → S 1 excitation energy (∆ E ex ). As training progressed, the ∆ E iso distribution extended toward higher values, while ∆ E ex values were more concentrated within the visible-light window, yielding candidates within the selected joint screening region, although neither descriptor was included in the reward. These results show that automated semi-empirical post-generation validation can identify candidates with targeted property combinations and reveal information beyond conventional molecular generation metrics.",
  "abstract_shown": true,
  "affiliations": [
    "Graduate School of Arts and Sciences, University of Tokyo, 3-8-1 Komaba, Meguro-ku, Tokyo, Japan, 153-8902",
    "Department of Chemistry, Advanced Materials Science and Engineering Center, and Institute for Energy Studies",
    "Western Washington University"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Qingyu Zhu"
    },
    {
      "affs": [
        1,
        2
      ],
      "name": "Ryan Lingg"
    },
    {
      "affs": [
        1,
        2
      ],
      "name": "Reuben Szabo"
    },
    {
      "affs": [
        1,
        2
      ],
      "name": "Tim Kowalczyk"
    },
    {
      "affs": [
        0
      ],
      "name": "Daisuke Yokogawa"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5p0mx5417paxa.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15009066/v1",
  "fulltext_url": null,
  "id": "5p0mx5417paxa",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009066/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": "W7213541364",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009066/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-18",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/5p0mx5417paxa.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:19Z",
      "native_id": "10.26434/chemrxiv.15009066",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009066/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "A Molecular Generation–Validation Workflow Combining Reversible Junction Tree Reinforcement Learning and Semi-empirical Quantum Chemistry: A Case Study on Molecular Solar Thermal Fuels",
  "title_text": "A Molecular Generation–Validation Workflow Combining Reversible Junction Tree Reinforcement Learning and Semi-empirical Quantum Chemistry: A Case Study on Molecular Solar Thermal Fuels",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:19Z",
  "url": "https://research.draconitic.com/paper/5p0mx5417paxa",
  "venue": "ChemRxiv",
  "versions": []
}