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 2606.05050cond-mat.mtrl-scics.AIphysics.chem-ph
收藏

自主异质催化剂发现:一种自进化多智能体数字孪生系统

Autonomous heterogeneous catalyst discovery with a self-evolving multi-agent digital twin

Department of Chemistry, Hong Kong University of Science and Technology(香港科技大学化学系);IAS Center for AI for Scientific Discoveries, Hong Kong University of Science and Technology(香港科技大学人工智能科学发现中心);Department of Computer Science and Engineering, Hong Kong University of Science and Technology(香港科技大学计算机科学与工程系);Department of Chemical and Biological Engineering, Hong Kong University of Science and Technology(香港科技大学化学与生物工程系)

Zhilong Song, Zongmin Zhang, Lixue Cheng

AI总结:

提出CatDT(催化数字孪生),一种自进化多智能体系统,通过集成八种专业智能体和27种科学工具,在单个GPU上5-30分钟内自动构建工作催化剂数字孪生,实现从体相晶体和自然语言反应描述到稳定晶面预测、反应路径枚举、过渡态定位和动力学计算的全流程,在七个气固相基准上预测与实验偏差在0.5-2倍内,并独立发现丙烷脱氢非贵金属候选催化剂。

摘要:

理论异质催化有望实现快速催化剂发现,然而计算和机器学习预测常常偏离实验,并局限于狭窄的材料家族,原因是缺乏忠实、条件感知的催化模拟器。我们提出CatDT(催化数字孪生),一种自进化多智能体系统,构建工作催化剂的自主数字孪生,统一了气固和液固建模。仅从体相晶体和自然语言反应描述出发,八个专业智能体和27种科学工具在单个GPU上5-30分钟内预测稳定晶面、重构工作表面、枚举和排序反应路径、定位过渡态并计算动力学。两项创新解决了最困难的步骤:UniMech通过融合智能体引导提议与能量缓存图搜索,以比穷举枚举低超过$10^3$倍的成本发现新型材料的主导路径;记忆增强的强化循环将600个催化表面的势垒计算成功率从41%提高到84%。在七个气固基准上——台阶金属、单原子催化剂、有序金属间化合物、富空位二维硫化物和碳化物,以及强金属-载体相互作用(SMSI)界面——每个CatDT预测在四个数量级内与实验偏差在0.5-2倍之间。对于丙烷脱氢,CatDT独立发现与Pt基工业基准相媲美的非贵金属候选催化剂,其中提出的Ni@ZrO$_2$ SMSI覆盖层在约100%选择性下达到$1.63~ ext{s}^{-1}$的模拟TOF。更广泛地说,忠实催化剂数字孪生——或任何多阶段科学模拟器——的决定性因素不是原始LLM能力,而是围绕它的工程化框架:确定性工具、持久记忆和跨模型、工具和运行累积的已验证自我改进。

英文摘要:

Theoretical heterogeneous catalysis promises rapid catalyst discovery, yet computational and machine-learning predictions often deviate from experiment and stay confined to narrow material families, for want of a faithful, condition-aware catalytic simulator. We present CatDT (Catalysis Digital Twin), a self-evolving multi-agent system that builds an autonomous digital twin of a working catalyst, unifying gas-solid and liquid-solid modeling. From only a bulk crystal and a natural-language reaction description, eight specialized agents and 27 scientific tools predict stable facets, reconstruct working surfaces, enumerate and rank reaction pathways, locate transition states, and compute kinetics in 5-30 min on a single GPU. Two innovations address the hardest steps: UniMech finds dominant pathways for novel materials at over $10^3\times$ lower cost than exhaustive enumeration by fusing agent-guided proposals with energy-cached graph search, and a memory-augmented reinforcement loop raises barrier-calculation success from 41% to 84% across 600 catalytic surfaces. Across seven gas-solid benchmarks -- stepped metals, single-atom catalysts, ordered intermetallics, vacancy-rich 2D sulfides and carbides, and a strong-metal--support-interaction (SMSI) interface -- every CatDT prediction lies within 0.5-2 times experiment over four orders of magnitude. For propane dehydrogenation, CatDT independently discovers non-precious candidates rivaling the Pt-based industrial benchmark, with a proposed Ni@ZrO$_2$ SMSI overlayer reaching a simulated TOF of $1.63~\text{s}^{-1}$ at $\sim$100% selectivity. More broadly, the decisive factor for a faithful catalyst digital twin -- or any multi-stage scientific simulator -- is not raw LLM capability but the engineered harness around it: deterministic tools, persistent memory, and verified self-improvement that compound across models, tools, and runs.

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。

↑