Archi: Agentic Operations at the CMS Experiment

• URL: http://arxiv.org/abs/2606.04755v1
• Date: Wed, 03 Jun 2026 11:38:30 GMT
• Title: Archi: Agentic Operations at the CMS Experiment
• Abstract summary: We present Archi, an open-source, end-to-end framework for scientific data ingestion.<n>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.<n>We evaluate the system on operator feedback and a question set collected from production usage, graded by human and automated panels.
• Score: 3.1746900537575597
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations [106.74348504930124]
  We introduce DocOps, a deterministically verifiable evaluation framework underpinned by a hierarchical taxonomy.<n>Based on DocOps, we systematically evaluate representative closed- and open-source models across various agentic harnesses.<n>Our work exposes the capability boundaries of agents in maintaining global document consistency, shedding light on the future design of robust, non-destructive agents.
  arXiv  Detail & Related papers  (2026-07-22T07:52:59Z)
• QwenPaw-Data: Bridging Facts, Methodology, and Execution for Autonomous Enterprise Data Analytics [45.48758200829718]
  We introduce QwenPaw-Data, an agentic data system designed for enterprise intelligent data analysis.<n>QwenPaw-Data consolidates heterogeneous assets into reusable, governable, and evolvable analysis assets, then turns natural-language requests into end-to-end analytical spanning data understanding, retrieval, analysis, report generation, and decision support.
  arXiv  Detail & Related papers  (2026-07-13T02:38:00Z)
• Agyn: A Multi-Agent System for Team-Based Autonomous Software Engineering [0.09046463333989574]
  Real-world software development is organized as a collaborative activity carried out by teams following shared methodologies.<n>We present a fully automated multi-agent system that explicitly models software engineering as an organizational process.<n>Our results suggest that replicating team structure, methodology, and communication is a powerful paradigm for autonomous software engineering.
  arXiv  Detail & Related papers  (2026-02-01T22:17:19Z)
• VDSAgents: A PCS-Guided Multi-Agent System for Veridical Data Science Automation [11.521235834823301]
  Large language models (LLMs) become increasingly integrated into data science for automated system design.<n>This paper provides VDSAgents, a multi-agent system grounded in the Predictability-Computability-Stability (PCS) principles.<n>We evaluate VDSAgents on nine datasets with diverse characteristics, comparing it with state-of-the-art end-to-end data science systems.
  arXiv  Detail & Related papers  (2025-10-28T12:07:50Z)
• Build Your Personalized Research Group: A Multiagent Framework for Continual and Interactive Science Automation [41.659285482346235]
  We present texttfreephdlabor, an open-source multiagent framework featuring textitfully dynamic determined by real-time agent reasoning.<n>The framework provides comprehensive infrastructure including textitautomatic context compaction, textitworkspace-based communication to prevent information degradation, textitmemory persistence across sessions, and textitnon-blocking human intervention mechanisms.
  arXiv  Detail & Related papers  (2025-10-17T13:13:32Z)
• LLM$\times$MapReduce-V3: Enabling Interactive In-Depth Survey Generation through a MCP-Driven Hierarchically Modular Agent System [55.33058620876928]
  LLM x MapReduce-V3 is a hierarchically modular agent system for long-form survey generation.<n>System captures research perspectives to generate a comprehensive skeleton, which is then developed into an in-depth survey.<n>Human evaluations demonstrate that our system surpasses representative baselines in both content depth and length.
  arXiv  Detail & Related papers  (2025-10-13T01:38:37Z)
• LLM-based Multi-Agent Blackboard System for Information Discovery in Data Science [69.1690891731311]
  We propose a novel multi-agent communication paradigm inspired by the blackboard architecture for traditional AI models.<n>In this framework, a central agent posts requests to a shared blackboard, and autonomous subordinate agents respond based on their capabilities.<n>We evaluate our method on three benchmarks that require explicit data discovery.
  arXiv  Detail & Related papers  (2025-09-30T22:34:23Z)
• Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First [72.85721148326138]
  Large Language Model (LLM) agents are likely to become the dominant workload for data systems in the future.<n>Agentic speculation can pose challenges for present-day data systems.<n>We outline a number of new research opportunities for a new agent-first data systems architecture.
  arXiv  Detail & Related papers  (2025-08-31T21:19:40Z)
• OpenCUA: Open Foundations for Computer-Use Agents [74.61449905487565]
  Vision-language models have demonstrated impressive capabilities as computer-use agents (CUAs)<n>We propose OpenCUA, a comprehensive open-source framework for scaling CUA data and foundation models.<n>Our end-to-end agent models demonstrate strong performance across CUA benchmarks.
  arXiv  Detail & Related papers  (2025-08-12T17:52:32Z)
• WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization [68.46693401421923]
  WebShaper systematically formalizes IS tasks through set theory.<n>WebShaper achieves state-of-the-art performance among open-sourced IS agents on GAIA and WebWalkerQA benchmarks.
  arXiv  Detail & Related papers  (2025-07-20T17:53:37Z)
• Deep Research Agents: A Systematic Examination And Roadmap [109.53237992384872]
  Deep Research (DR) agents are designed to tackle complex, multi-turn informational research tasks.<n>In this paper, we conduct a detailed analysis of the foundational technologies and architectural components that constitute DR agents.
  arXiv  Detail & Related papers  (2025-06-22T16:52:48Z)
• DECO: Life-Cycle Management of Enterprise-Grade Copilots [9.908567982584815]
  DECO is a comprehensive framework for developing, deploying, and managing enterprise-grade copilots.<n>It supports efficient and customized retrieval-augmented-generation (RAG) algorithms.<n>DECO has demonstrated its effectiveness through widespread adoption, enabling tens of thousands of interactions.
  arXiv  Detail & Related papers  (2024-12-08T23:00:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.