La Agente Óptima: Towards Agentic Self-Driving Laboratories

📄 arXiv: 2609.04564v1 📥 PDF

作者: Marcel Müller, Jiaru Bai, Willi Gottstein, Abhijoy Mandal, Mohammad Nazeri, Elia Savino, Yanlin Fang, Sujoy Das, Sergio Pablo García Carrillo, Yeonghun Kang, Juan B. Pérez-Sánchez, Simone Pilon, Martin Fitzner, Timothy Noël, Frank Gu, Varinia Bernales, Alán Aspuru-Guzik

分类: cs.AI, cs.MA, physics.chem-ph

发布日期: 2026-09-03


💡 一句话要点

提出La Agente Óptima框架以优化自驾实验室的决策过程

🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)

关键词: 自驾实验室 贝叶斯优化 自动化实验 科学发现 大语言模型 实验优化 决策支持

📋 核心要点

  1. 现有自驾实验室依赖人类专家进行实验目标的设定与调整,限制了自动化程度和效率。
  2. La Agente Óptima框架通过贝叶斯优化实现自动化决策,减少对人类专家的依赖,提升实验效率。
  3. 在多项实验中,Óptima显著提高了实验产率,并在资源使用上优于人类主导的实验方案。

📝 摘要(中文)

自驾实验室(SDLs)结合自动化实验与自适应决策,以加速科学发现。然而,其操作往往依赖于人类专家将科学目标转化为可执行的闭环实验。本文提出La Agente Óptima,一个代理框架,能够在计算和实验系统中构建和监督贝叶斯优化活动,同时保持持续的优化状态。Óptima将大型语言模型(LLM)的推理与执行活动分离,确保在进展需要解释或修订时才将控制权返回给代理。通过一系列实验,Óptima在科学问题和执行环境变化的情况下,持续维护可执行的实验活动,展现了其在优化效率和材料使用上的优势。

🔬 方法详解

问题定义:本文旨在解决自驾实验室中人类专家对实验目标设定的依赖性,现有方法在动态环境下难以持续优化实验过程。

核心思路:La Agente Óptima框架通过贝叶斯优化实现自动化决策,分离推理与执行,确保在必要时才将控制权返回给代理,从而提高实验的自动化程度与效率。

技术框架:该框架包括多个模块:1) 贝叶斯优化模块,负责优化决策;2) 数据监控模块,实时跟踪实验进展;3) 决策审计模块,确保每一步决策的可追溯性。

关键创新:Óptima的创新在于将LLM推理与实验执行分离,使得优化过程能够在不需要人类干预的情况下持续进行,显著提高了实验的自动化水平。

关键设计:在设计中,Óptima采用了高效的贝叶斯优化算法,并设置了适应性参数,以应对实验环境的变化,同时确保每个决策的可审计性。实验中使用的损失函数和优化目标均经过精心设计,以最大化实验产出。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

在闭环接触角优化实验中,Óptima成功识别并纠正了中途测量失败,将接触角从71.4度降低至67.8度,接近目标范围。同时,在为期五天的多目标流动化学实验中,Óptima将产率从30%提升至59%,显示出其在优化效率和材料使用上的显著优势。

🎯 应用场景

该研究的潜在应用领域包括化学合成、材料科学和生物医学等领域,能够帮助科学家在复杂实验中实现更高的自动化和效率。未来,Óptima框架有望推广至更多科学研究领域,推动科学发现的速度与质量。

📄 摘要(原文)

Self-driving laboratories (SDLs) combine automated experimentation with adaptive decision-making to accelerate scientific discovery. Their operation nevertheless often depends on human specialists who translate scientific objectives into executable closed-loop campaigns. Specialists adjust them as data and operating conditions change. Here, we present La Agente Óptima, an agentic framework that constructs and supervises Bayesian optimization campaigns across computational and experimental systems while maintaining a persistent optimization state. By separating large language model (LLM) reasoning from executed campaigns, Óptima runs repetitive optimization loops consistently, returns control to the agent only when progress requires interpretation or campaign revision, and keeps every decision auditable. We evaluate Óptima across ablation studies, five digital discovery tasks, and two physical platforms. Throughout, Óptima maintained executable campaigns as both the scientific problem and execution environment evolved. In a closed-loop contact angle optimization campaign, Óptima identified and corrected a mid-run measurement failure, bringing the contact angle from 71.4 to 67.8 degrees, just above the 64-66 degree range. From this result, Óptima correctly inferred that the target was likely unattainable with the available reagents and recommended changing the formulation. In a five-day multi-objective flow-chemistry campaign, Óptima increased the yield from 30% to 59% over 23 experiments. Despite substantial inference costs, it cost less and used substantially less starting material than a human-directed campaign, while selecting a more mass-efficient operating point. These results show that LLM-based agents can make rigorous, long-running optimization campaigns accessible to domain scientists without specialist setup, expanding the scope of SDLs.