跳到正文
arXiv cs.AI· Xin-De Wang, Zhi-Rui Chen, Ze-Feng Gao, Peng-Jie Guo, Cheng Mu, Zhong-Yi Lu·· 4 小时前AI 评分34

LEAP:LLM 驱动的钙钛矿前驱体添加剂闭环发现框架

A closed-loop framework for perovskite precursor additive discovery

AI 导读

LEAP 是一个结合领域专用语言模型与主动学习的闭环框架,可在低数据条件下优先筛选钙钛矿前驱体添加剂。模型从文献提取机理知识并转为可解释分子描述符,用于不确定性感知的贝叶斯优化;在未见文献评测中,其机理一致性优于所测试的通用模型。专家引导的概念验证中,两个后期轮次添加剂将器件平均光电转换效率提升至 20.13% 和 20.87%(对照组 19.25%),最佳器件达 21.32%。

正文 · 原文

View PDF HTML (experimental)

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. Here we show that LEAP (LLM-driven Exploration via Active Learning for Perovskites), a closed-loop framework combining a domain-specialized language model with active learning, prioritizes perovskite precursor additives under low-data conditions. The model extracts mechanism-relevant knowledge from the literature and converts it into interpretable molecular descriptors for uncertainty-aware Bayesian optimization. On an evaluation drawn from unseen literature, the specialized model provides more mechanism-consistent answers than the tested general-purpose models. In an expert-guided proof-of-concept study, two later-round additives increase average device power conversion efficiencies to 20.13% and 20.87%, compared with 19.25% for the control, and the best device reaches 21.32%. Because only a limited number of candidates are tested prospectively, these results provide preliminary evidence that literature-grounded molecular representations, Bayesian optimization, and expert assessment can support additive discovery for perovskite solar cells.
Comments: 30 pages; 11 figures
Subjects: Machine Learning (cs.LG); Materials Science (cond-mat.mtrl-sci); Artificial Intelligence (cs.AI); Chemical Physics (physics.chem-ph)
Cite as: arXiv:2605.20242 [cs.LG]
  (or arXiv:2605.20242v2 [cs.LG] for this version)
  https://doi.org/10.48550/arXiv.2605.20242

arXiv-issued DOI via DataCite

Related DOI: https://doi.org/10.1038/s43246-026-01407-3

DOI(s) linking to related resources

Submission history

From: Xin-De Wang [view email]
[v1] Mon, 18 May 2026 02:50:37 UTC (6,055 KB)
[v2] Tue, 17 Nov 2026 05:05:00 UTC (5,770 KB)

来源:arXiv cs.AI · arxiv.org