CMS实验用智能代理系统自动处理技术运维问题
Archi: Agentic Operations at the CMS Experiment
- 构建可配置的私有智能体，整合文档、历史数据与实时监控
- 在真实运维场景中准确回答操作员问题，解决率超80%
- 本地部署开源模型，保障敏感数据隐私安全
我们提出Archi，一个开源的端到端框架，用于科学合作项目，能系统化地摄入和组织异构数据源，并部署可配置、私有且可扩展的智能体来检索和推理这些数据。自2026年2月起，该系统已在欧洲核子研究中心大型强子对撞机（LHC）的CMS实验计算运维团队中部署，作为技术支持代理，为技术操作员提供结合文档、历史数据和实时监控系统的检索与分析能力。我们通过运维人员反馈及生产环境中收集的问题集进行评估，由人工与自动化团队评分。结果表明，系统在实际运维任务中表现有效，能够解决真实问题。此外，本地部署的开源权重模型表现竞争力，支持敏感数据的完全私有管理。
原文摘要 · Abstract (English)
We present Archi, an open-source, end-to-end framework for scientific collaborations that combines the systematic ingestion and organization of heterogeneous data sources with the deployment of configurable, private, and extensible agents that retrieve and reason over them. An instance of Archi has been deployed for the Computing Operations team of the CMS experiment at CERN's LHC since February 2026 as a support agent for technical operators, offering retrieval and analysis capabilities by combining documentation, historical data, and live monitoring systems. We evaluate the system on operator feedback and a question set collected from production usage, graded by human and automated panels. The system proves effective at operational tasks, resolving real-world queries posed by CMS operators. We also observe that locally-hosted, open-weight models perform competitively, enabling fully private management of sensitive data.
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。