Scholarlink

<p>Covalent organic frameworks (COFs) are promising photocatalysts for solar hydrogen production, yet the most electronically favorable linkages, imines,hydrolyze rapidly in water, creating a stability-activity trade-off that limits practical deployment. Navigating the combinatorial design space of nodes, linkers, linkages, and functional groups to identify candidates that are simultaneously active and durable remains a formidable challenge. Here we introduce <b>Ara</b>, a large-language-model (LLM) agent that leverages pretrained chemical knowledge, donor-acceptor theory, conjugation effects, and linkage stability hierarchies, to guide the search for photocatalytic COFs satisfying joint band-gap, band-edge, and hydrolytic-stability criteria. Evaluated against random search and Bayesian optimization (BO) over a space consisting of candidates with various nodes, linkers, linkages, and r-groups, screened with a GFN1-xTB fragment pipeline, Ara achieves a 52.7% hit rate (11.5 × random, <i>p</i> = 0.006), finds its first hit at iteration 12 versus 25 for random search, and significantly outperforms BO (<i>p</i> = 0.006). Inspection of the agent’s reasoning traces reveal interpretable chemical logic: early convergence on vinylene and <i>β</i>-ketoenamine linkages for stability, node selection informed by electron-withdrawing character, and systematic R-group optimization to center the band gap at 2.0 eV. Exhaustive evaluation of the full search space uncovers a complementary exploitation-exploration trade-off between the agent and BO, suggesting that hybrid strategies may combine the strengths of both approaches. These results demonstrate that LLM chemical priors can substantially accelerate multi-criteria materials discovery.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Escaping the hydrolysis trap: a react agent for inverse design of durable photocatalytic covalent organic frameworks

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月3日

查看全文
  • Iman Peivaste,
  • Nicolas D. Boscher,
  • Ahmed Makradi,
  • Salim Belouettar

摘要

Covalent organic frameworks (COFs) are promising photocatalysts for solar hydrogen production, yet the most electronically favorable linkages, imines,hydrolyze rapidly in water, creating a stability-activity trade-off that limits practical deployment. Navigating the combinatorial design space of nodes, linkers, linkages, and functional groups to identify candidates that are simultaneously active and durable remains a formidable challenge. Here we introduce Ara, a large-language-model (LLM) agent that leverages pretrained chemical knowledge, donor-acceptor theory, conjugation effects, and linkage stability hierarchies, to guide the search for photocatalytic COFs satisfying joint band-gap, band-edge, and hydrolytic-stability criteria. Evaluated against random search and Bayesian optimization (BO) over a space consisting of candidates with various nodes, linkers, linkages, and r-groups, screened with a GFN1-xTB fragment pipeline, Ara achieves a 52.7% hit rate (11.5 × random, p = 0.006), finds its first hit at iteration 12 versus 25 for random search, and significantly outperforms BO (p = 0.006). Inspection of the agent’s reasoning traces reveal interpretable chemical logic: early convergence on vinylene and β-ketoenamine linkages for stability, node selection informed by electron-withdrawing character, and systematic R-group optimization to center the band gap at 2.0 eV. Exhaustive evaluation of the full search space uncovers a complementary exploitation-exploration trade-off between the agent and BO, suggesting that hybrid strategies may combine the strengths of both approaches. These results demonstrate that LLM chemical priors can substantially accelerate multi-criteria materials discovery.