用自然语言自动执行粒子加速器多阶段实验，效率提升百倍且安全可控。
Agentic Artificial Intelligence for Multistage Physics Experiments at a Large-Scale User Facility Particle Accelerator
- 通过自然语言生成实验计划，整合数据检索与设备控制流程。
- 实验准备时间缩短近百倍，专家操作亦显著提速。
- 适合加速器物理研究者及大型科学装置运维人员使用。
我们首次展示了一种基于语言模型的自主代理人工智能系统，可在生产级同步辐射光源上全自动执行多阶段物理实验。该系统部署于先进光源（Advanced Light Source）粒子加速器，将用户自然语言指令转化为包含档案数据检索、控制系统通道解析、自动化脚本生成、受控机器交互和分析的结构化执行方案。在典型的机器物理任务中，相较于人工编写脚本，准备时间缩短了两个数量级，即使对系统专家而言也如此；同时严格遵守操作标准安全约束。核心架构特性包括：先规划后执行、工具访问受限、动态能力选择，实现了透明可审计的执行过程，并保证完全可复现的实验产物。这些成果为安全引入代理型AI于加速器实验与复杂机器物理研究提供了范式，具备全球加速器间的直接可迁移性，更广泛适用于其他大型科学基础设施。
原文摘要 · Abstract (English)
We present the first language-model-driven agentic artificial intelligence (AI) system to autonomously execute multi-stage physics experiments on a production synchrotron light source. Implemented at the Advanced Light Source particle accelerator, the system translates natural language user prompts into structured execution plans that combine archive data retrieval, control-system channel resolution, automated script generation, controlled machine interaction, and analysis. In a representative machine physics task, we show that preparation time was reduced by two orders of magnitude relative to manual scripting even for a system expert, while operator-standard safety constraints were strictly upheld. Core architectural features, plan-first orchestration, bounded tool access, and dynamic capability selection, enable transparent, auditable execution with fully reproducible artifacts. These results establish a blueprint for the safe integration of agentic AI into accelerator experiments and demanding machine physics studies, as well as routine operations, with direct portability across accelerators worldwide and, more broadly, to other large-scale scientific infrastructures.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。