研究人员开发了“La Agente Óptima”，一个旨在自动化和监督科学发现的贝叶斯优化活动的自主代理框架。该框架将大型语言模型推理与实验执行分离，实现了持久的优化状态和可审计的决策。Óptima 已证明其在数字和物理平台上维护和调整活动的能力，包括在接触角优化中识别和纠正测量失败，以及在流动化学实验中提高产率。该系统旨在使没有专业设置的科学家更容易进行复杂的优化过程，从而扩展自主实验室的能力。 AI
影响 该框架可以通过使复杂、自动化的实验更容易被研究人员使用，从而加速科学突破。
排序理由 该集群描述了一篇详细介绍用于科学发现的新型自主代理框架的研究论文。
在 arXiv cs.MA (Multiagent) 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2609.04564v1 Announce Type: new Abstract: 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…
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. Speciali…
<blockquote><p><i><b><span>Context</span></b></i><i><span>: This is inspired by my first ever piece I wrote on anything AI safety related when I discovered AI safety was a thing back in March 2026, published originally on my Substack. The version here has been modified to represe…