{
  "abstract": "Efficient discovery of precursor additives is essential for improving the performance of perovskite solar cells, yet the large chemical space makes conventional trial-and-error screening inefficient. We develop LEAP(LLM-driven Exploration via Active Learning for Perovskites), an expert-in-the-loop closed framework that couples a domain-specialized large language model(LLM) with active learning for iterative additive prioritization. The LLM is trained to extract mechanism-relevant knowledge from the perovskite additive literature and to represent candidate molecules through interpretable descriptors, which are further integrated into a Bayesian optimization workflow for uncertainty-aware prioritization under low-data conditions. Benchmark results on unseen literature show that the domain-specialized model outperforms general-purpose models in mechanism-consistent reasoning. Experimental validation in an expert-in-the-loop proof-of-concept study suggests improved additive prioritization across three screening rounds, leading to average device PCEs of 20.13% and 20.87% for the later-round 6-CDQ- and 2-CNA-treated devices, respectively, compared with 19.25% for the control, with a champion PCE of 21.32%. These results provide preliminary evidence that literature-grounded mechanistic descriptors, when coupled with Bayesian optimization and expert feasibility review, can support mechanism-aware additive prioritization in perovskite photovoltaics.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2605.20242",
  "author_total": 6,
  "authors": [
    {
      "name": "Xin-De Wang"
    },
    {
      "name": "Zhi-Rui Chen"
    },
    {
      "name": "Ze-Feng Gao"
    },
    {
      "name": "Peng-Jie Guo"
    },
    {
      "name": "Cheng Mu"
    },
    {
      "name": "Zhong-Yi Lu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/ddgjjckbnz5h5.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2605.20242",
  "fulltext_url": null,
  "id": "ddgjjckbnz5h5",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2605.20242",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cond-mat.mtrl-sci"
    ],
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "physics.chem-ph"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2605.20242",
  "pmcid": null,
  "pmid": null,
  "published": "2026-05-18",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/ddgjjckbnz5h5.ris",
  "sources": [
    {
      "first_seen": "2026-11-10T06:21:23Z",
      "native_id": "2605.20242",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2605.20242"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "arxiv:physics.chem-ph",
      "subfield": "physical"
    },
    {
      "field": "physics",
      "origin": "arxiv:cond-mat.mtrl-sci",
      "subfield": "condensed-matter"
    }
  ],
  "title": "LEAP: A closed-loop framework for perovskite precursor additive discovery",
  "title_text": "LEAP: A closed-loop framework for perovskite precursor additive discovery",
  "type": "preprint",
  "updated_at": "2026-11-10T06:21:23Z",
  "url": "https://research.draconitic.com/paper/ddgjjckbnz5h5",
  "venue": "arXiv",
  "versions": [
    {
      "doi": "10.1038/s43246-026-01407-3",
      "pid": null,
      "relation": "published-as",
      "title": null,
      "venue": null
    }
  ]
}