Archi: Agentic Operations at the CMS Experiment
This work provides a practical, private, and extensible AI assistant for scientific operations teams, addressing the need for efficient data retrieval and reasoning in large-scale experiments.
Archi is an open-source framework for scientific collaborations that integrates heterogeneous data sources with configurable agents for retrieval and reasoning. Deployed for CMS experiment operations since February 2026, it effectively resolves real-world operator queries, with locally-hosted open-weight models performing competitively.
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.