Agentic-MatriBO:面向材料与化学设计的能力编译式智能体贝叶斯优化
Agentic-MatriBO: Capability-Compiled Agentic Bayesian Optimization for Materials and Chemical Design
AI总结:
本文提出Agentic-MatriBO框架,将BO组件与选择条件表示为可组合能力,在四个材料化学任务上与八个基线对比,其在多数任务中表现最优,验证了能力编译模块的有效性。
摘要:
材料与化学优化需在有限预算下,从序列观测结果中选择下一次合成、表征或高保真模拟方案。大语言模型可利用任务知识提出调整方案,但组合代理模型、获取函数与搜索策略时会受兼容性、参数依赖及证据要求的限制。本文提出Agentic-MatriBO,一种能力编译式智能体贝叶斯优化(BO)框架,该框架将BO组件与选择条件表示为可组合的能力。语言策略模块提出BO方案与候选计划;编译器模块会对照已注册的能力目录检查提案;确定性执行层则验证并确定候选方案。Oracle观测结果存储于研究记忆中,为后续迭代提供信息。我们在四个离线有限候选池(COF、PCE10、Buchwald–Hartwig(BH)、Suzuki–Miyaura)上,将Agentic-MatriBO与八个基线方法进行对比,每个条件使用五个随机种子,结果以描述性方式呈现。在四个任务中,Agentic-MatriBO在将每个目标定向为越高越好后,获得了最佳的平均终点质量。在COF任务中,无论是端到端对比还是共享初始化后,它在全部五个种子中均达到了表格列出的最优值,且在累积质量上也保持优势。其在BO阶段的最优质量曲线下归一化面积(nAUC-BO)在COF上显著更高,在PCE10和BH上与最佳基线接近持平,在Suzuki上则较低。COF的 ablation实验表明,移除能力编译器或证据门会导致累积质量降低,且精确最优值命中次数减少。该框架为基于证据的BO适配提供了可检查的接口。
英文摘要:
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.
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。