发表机构
Argonne National Laboratory（阿贡国家实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文基于APS部署经验，提出在科学用户设施中生产部署AI智能体的策略，涵盖束线控制、知识检索和数据分析，强调跨设施可复用的设计原则。
AI 中文摘要
智能体人工智能（AI）正从研究演示走向科学用户设施的生产应用，包括光源、中子源、纳米科学中心和自主实验室。其科学价值不仅在于提高吞吐量。智能体可以执行校准、测量执行和质量控制中的可重复任务，以及将数据转化为可审查证据的初步分析，使科学家能够专注于假设、意外观察和解释。借鉴在APS部署LLM驱动智能体的经验，本观点提炼了实用策略，重点强调可在不同仪器和设施间复用的要素。我们讨论了用于束线控制、设施知识检索和数据分析的智能体框架，同时保持底层设计原则独立于任何具体实现。这些原则涵盖推理端点、工具服务器架构、非文本数据、计算密集型服务、可复用技能以及仪器生命周期内的受治理学习。我们还考虑了网络和Linux操作、受治理共享内存和确定性编排如何将这些模式扩展到设施服务中。由于LLM能力持续演进，这些建议代表了封面日期时的技术快照。
英文摘要
Agentic artificial intelligence (AI) is moving beyond research demonstrations toward production use at scientific user facilities, including light sources, neutron sources, nanoscience centers, and autonomous laboratories. Its scientific value extends beyond increasing throughput. Agents can perform repeatable tasks in calibration, measurement execution, and quality control, as well as initial analyses that turn data into reviewable evidence, allowing scientists to focus on hypotheses, unexpected observations, and interpretation. Drawing on deployments of LLM-driven agents at the APS, this perspective distills practical strategies with an emphasis on elements that can be reused across instruments and facilities. We discuss agent harnesses for beamline control, facility knowledge retrieval, and data analysis while keeping the underlying design principles independent of any specific implementation. These principles cover inference endpoints, tool-server architectures, non-text data, computationally intensive services, reusable skills, and governed learning throughout an instrument's lifecycle. We also consider how network and Linux operations, governed shared memory, and deterministic orchestration can extend these patterns across facility services. Because LLM capabilities continue to evolve, these recommendations represent a snapshot of the technology as of the date on the cover.
