发表机构
Texas A&M University（德克萨斯农工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出一种智能体资源分配框架，用于批量多目标贝叶斯优化，通过自适应策略调整在资源约束下平衡探索与利用，显著提升合金材料发现效率并减少预测不确定性。
AI 中文摘要
先进材料的发现与开发是一个充满挑战的过程，受到合成、加工和表征环节的高时间与高经济成本制约。其底层设计空间可能极为庞大，且通常包含多个相互竞争的目标。贝叶斯优化（BO）为高效探索此类空间提供了一种原则性方法，但大多数工作流程依赖于固定的探索-利用策略，缺乏在自主实验室典型的动态活动中适应不断变化约束的能力。在本工作中，我们开发了一种在资源约束下用于合金设计的多目标贝叶斯优化框架，并对每次迭代的自适应策略调整方法进行了基准测试。我们的评估涵盖了一个七元难熔高熵合金（RHEA）系统，聚焦于最大化熔点和最小化密度，以及一个基于Fe-Co-Ni的软磁合金系统，目标是饱和磁化强度、矫顽力和硬度。我们比较了一种以利用为主的策略、一种固定的混合探索/利用策略，以及两种不同的基于LLM的自适应策略，它们在批量分配和活动信号解释方面采用不同方法，并在基线和活动中期资源事件条件下进行评估，包括预算削减、时间线缩短和组合干扰。我们的结果表明，混合分配策略比以利用为主的基线累积了显著更多的互信息，而超体积和优化速度的代价相对较小，自适应策略通过根据不断变化的活动统计数据和资源约束调整其分配，优于固定混合分配策略。这些发现表明，自适应资源分配为材料发现活动提供了一种有利的权衡，能够减少帕累托最优成分上的预测不确定性。
英文摘要
The discovery and development of advanced materials is a challenging process constrained by the high time and monetary costs of synthesis, processing, and characterization. The underlying design spaces can be enormous, often with multiple competing objectives. Bayesian optimization (BO) provides a principled approach for efficiently navigating such spaces, but most workflows rely on fixed exploration-exploitation policies that lack the capacity to adapt to shifting constraints in dynamic campaigns typical of self-driving laboratories. In this work, we develop a multi-objective BO framework for alloy design under resource constraints, benchmarking strategies for adaptive policy tuning at each iteration. Our evaluation covers a septenary refractory high-entropy alloy (RHEA) system focused on maximizing melting temperature and minimizing density, and an Fe-Co-Ni-based soft magnetic alloy system targeting saturation magnetization, coercivity, and hardness. We compare an exploitation-focused strategy, a fixed mixed exploratory/exploitative policy, and two distinct LLM-based adaptive strategies with different approaches to batch allocation and campaign signal interpretation, evaluated across baseline and mid-campaign resource event conditions including budget reductions, timeline cuts, and combined disruptions. Our results show that mixed allocation strategies accumulate substantially more mutual information than the exploitation-focused baseline at a proportionally smaller cost to hypervolume and optimization speed, with adaptive strategies outperforming a fixed-mixed allocation policy by adjusting their allocation in response to both evolving campaign statistics and resource constraints. These findings suggest that adaptive resource allocation offers a favorable tradeoff for materials discovery campaigns in reducing predictive uncertainty on Pareto-optimal compositions.
Comments36 pages, 8 Main Text Figures, 2 Main Text Tables, 3 Appendix Sections
