Archi: Agentic Operations at the CMS Experiment
2026-06-03 • Artificial Intelligence
Artificial IntelligenceInformation Retrieval
AI summaryⓘ
The authors developed Archi, an open-source tool that helps scientists work together by collecting and organizing different kinds of data. They set it up for a team at CERN to assist with running the Large Hadron Collider by answering questions and analyzing information from documents, past records, and live systems. They tested Archi using real user feedback and questions, finding it useful for daily tasks. The authors also showed that using local AI models keeps sensitive information private while still working well.
Scientific collaborationData ingestionHeterogeneous dataConfigurable agentsCERNLarge Hadron Collider (LHC)CMS experimentLive monitoringOpen-source softwareLocal AI models
Authors
Pietro Lugato, Luca Lavezzo, Jason Mohoney, Hasan Ozturk, Muhammad Hassan Ahmed, Juan Pablo Salas, Viphava Ohm, Krittin Phornsiricharoenphant, Gabriele Benelli, Mariarosaria D'Alfonso, Manasvita Joshi, Warren Nam, Aron Soha, Samantha Sunnarborg, Austin Swinney, Jack Tucker, Dmytro Kovalskyi, Tim Kraska, Christoph Paus
Abstract
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.