arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2511.22307cs.AIcs.LG
收藏

通过知识引导语言模型反馈增强双钙钛矿的条件生成

Enhanced Conditional Generation of Double Perovskite by Knowledge-Guided Language Model Feedback

Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院(KAIST))

Inhyo Lee, Junhyeong Lee, Jongwon Park, KyungTae Lim, Seunghwa Ryu

AI总结:

本研究提出了一种多智能体框架,通过知识引导的文本梯度提升双钙钛矿生成的稳定性与有效性。

摘要:

双钙钛矿(DPs)因其组分可调性和低能耗制备工艺,成为可持续能源技术的有希望候选者,但其广阔的設計空間對條件材料發現提出了重大挑戰。本工作引入了一種多智能體、文本梯度驅動的框架,通過整合三種補充的反饋來源:基於LLM的自我評估、專門針對DP的領域知識引導反饋以及基於ML的替代反饋,來在自然語言條件下生成DP組分。類似於知識引導機械學習如何提高傳統數據驅動模型的可靠性,本框架通過將領域知識引導的文本梯度融入生成過程,使生成過程朝向DP組分空間中物理上 meaningful 的區域。系統比較了三種逐步配置,(i)純LLM生成,(ii)基於LLM推理的反饋生成LLM生成,(iii)基於領域知識引導反饋的LLM生成,結果顯示,迭代指導知識引導的梯度可提高穩定條件的滿足度,而無需額外訓練數據,實現超過98%的組分有效性,以及最高54%的穩定或過渡穩定候選者,超過了純LLM基線(43%)和先前GAN基結果(27%)。對基於ML的梯度的分析進一步揭示,它們在分布內(ID)區域中提高性能,但在分布外(OOD)區域中變得不可靠。總體而言,本工作提供了多智能體、知識引導文本梯度在DP發現中的首次系統分析,并建立了可用于MAS驅動生成材料設計的通用藍圖,以推動可持續技術的發展。

英文摘要:

Double perovskites (DPs) are promising candidates for sustainable energy technologies due to their compositional tunability and compatibility with low-energy fabrication, yet their vast design space poses a major challenge for conditional materials discovery. This work introduces a multi-agent, text gradient-driven framework that performs DP composition generation under natural-language conditions by integrating three complementary feedback sources: LLM-based self-evaluation, DP-specific domain knowledge-informed feedback, and ML surrogate-based feedback. Analogous to how knowledge-informed machine learning improves the reliability of conventional data-driven models, our framework incorporates domain-informed text gradients to guide the generative process toward physically meaningful regions of the DP composition space. Systematic comparison of three incremental configurations, (i) pure LLM generation, (ii) LLM generation with LLM reasoning-based feedback, and (iii) LLM generation with domain knowledge-guided feedback, shows that iterative guidance from knowledge-informed gradients improves stability-condition satisfaction without additional training data, achieving over 98% compositional validity and up to 54% stable or metastable candidates, surpassing both the LLM-only baseline (43%) and prior GAN-based results (27%). Analyses of ML-based gradients further reveal that they enhance performance in in-distribution (ID) regions but become unreliable in out-of-distribution (OOD) regimes. Overall, this work provides the first systematic analysis of multi-agent, knowledge-guided text gradients for DP discovery and establishes a generalizable blueprint for MAS-driven generative materials design aimed at advancing sustainable technologies.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑