arXiv cs.AI· Yu Zeng, Yuchuan Chen, Ziyue Zhang, Zijian Wei, Yanyi Su, Guojiang Zhao, Hongshuai Wang, Zhifeng Gao·· 3 天前AI 评分24
Agentic-MatriBO：面向材料与化学设计的 capability-compiled 智能体贝叶斯优化框架
Agentic-MatriBO: Capability-Compiled Agentic Bayesian Optimization for Materials and Chemical Design
AI 导读
研究者提出 Agentic-MatriBO，一个将贝叶斯优化组件与选择条件表示为可组合能力的智能体 BO 框架，由语言策略提出 BO 配方与候选方案、编译器对照能力目录校验、确定性执行层验证并提交候选。
正文 · 原文
Abstract:Materials and chemical optimization must choose the next synthesis, characterization, or high-fidelity simulation from sequential observations under a limited budget. Large language models can use task knowledge to propose adjustments, but composing surrogates, acquisition functions, and search strategies is constrained by compatibility, parameter dependencies, and evidence requirements. We present Agentic-MatriBO, a capability-compiled agentic Bayesian optimization (BO) framework that represents BO components and selection conditions as composable capabilities. A language policy proposes BO recipes and candidate plans; a compiler checks proposals against the registered capability catalog; and a deterministic execution layer validates and commits candidates. Oracle observations are stored in research memory and inform later rounds. We compare Agentic-MatriBO with eight baselines on four offline finite candidate pools---COF, PCE10, Buchwald--Hartwig (BH), and Suzuki--Miyaura---using five seeds per condition; results are reported descriptively. Across the four tasks, Agentic-MatriBO has the best mean endpoint quality after orienting each objective so that higher is better. On COF, it reaches the tabulated optimum in all five seeds both in the end-to-end comparison and after shared initialization, where it also retains an advantage in cumulative quality. Its normalized area under the best-so-far quality curve during the BO stage (nAUC-BO) is substantially higher on COF, near parity with the best baseline on PCE10 and BH, and lower on Suzuki. COF ablations show that removing the capability compiler or evidence gate coincides with lower cumulative quality and fewer exact-optimum hits. The framework provides an inspectable interface for evidence-conditioned BO adaptation.
| Comments: | 28 pages, 9 figures, supplementary information included |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.17832 [cs.LG] |
| (or arXiv:2610.17832v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.17832 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yu Zeng [view email]
[v1]
Tue, 13 Oct 2026 06:50:13 UTC (10,250 KB)
来源：arXiv cs.AI · arxiv.org