发表机构
University of Delaware; National Institute for Materials Science（特拉华大学; 物质材料研究机构）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出一种由AI智能体驱动的端到端量子输运测量工作流程，通过FermiLink框架安全操作低温仪器，在MoS2器件上实现多日自主测量，确定了自旋轨道耦合能并绘制相图，向自驱动实验室迈进。
AI 中文摘要
人工智能（AI）智能体正开始进入实验实验室，自动化实验并加速科学发现。在此，我们介绍一种AI驱动的工作流程，其中AI智能体端到端地执行多步骤、多天的量子输运测量。具体而言，在给定简短指令后，该智能体首先规划多步骤测量，然后安全操作低温仪器，分析数据，并最终生成报告。我们在多个单层和双层MoS2器件上演示了这一AI工作流程。通过持续长达六天的自主测量活动，该智能体确定了单层MoS2中导带自旋轨道耦合能，并绘制了双层MoS2中层分辨和谷分辨的相图。该实验工作流程通过FermiLink智能体框架实现，该框架强调仪器安全以及测量和分析的可靠性。该框架具有通用性，可轻松适应其他类型的实验，代表着向自驱动实验室迈进的一步。
英文摘要
Artificial-intelligence (AI) agents are beginning to enter experimental laboratories, automating experiments and accelerating scientific discovery. Herein, we introduce an AI-driven workflow in which an AI agent performs multi-step, multi-day quantum transport measurements end-to-end. Specifically, given brief instructions, the agent starts by planning the multi-step measurements, then safely operates the cryogenic instruments, analyzes the data, and concludes with a final report. We demonstrate this AI workflow on multiple monolayer and bilayer MoS2 devices. Through autonomous measurement campaigns lasting up to six days, the agent determined the conduction-band spin-orbit coupling energy in monolayer MoS2, and mapped a layer- and valley-resolved phase diagram in bilayer MoS2. This experimental workflow is implemented through the FermiLink agent harness, which emphasizes instrumental safety and the reliability of the measurement and analysis. The framework is general and can be readily adapted to other types of experiments, representing a step toward self-driving laboratories.
