Oct 19 – 23, 2026
CERN
Europe/Zurich timezone

Contribution List

54 out of 54 displayed
  1. Pietro Lugato (Massachusetts Inst. of Technology (US))
    10/19/26, 10:00 AM
    1
  2. Jason Mohoney (Massachusetts Inst. of Technology (US))
    10/19/26, 10:30 AM
  3. Maurizio Pierini (CERN)
    10/19/26, 11:30 AM

    Update from CERN AI Strategy.

    Go to contribution page
  4. Paulo Guilherme Pinheiro Pereira
    10/19/26, 12:00 PM

    Large language models are becoming part of everyday work at CERN, from writing code to analysing documents. The CERN AI Gateway (aigw.cern.ch) provides a single, CERN-managed entry point to these models. This talk introduces the platform and its main features. Through a live demo, we will show how to create an API key and call a model. Attendees will leave being able to start using the AI...

    Go to contribution page
  5. Jose Carlos Luna Duran (CERN)
    10/19/26, 2:00 PM

    Agents gone wild: You said what, somebody else said how, nobody said stop

    Go to contribution page
  6. Josh Bendavid (CERN)
    10/19/26, 2:30 PM
  7. Antonio Battaglia (Chulalongkorn University (TH)), Dmytro Kovalskyi (Massachusetts Inst. of Technology (US)), Hasan Ozturk (CERN), Jason Mohoney (Massachusetts Inst. of Technology (US)), Juan Pablo Salas Galindo (University of Wisconsin (US)), Luca Lavezzo (MIT), Pietro Lugato (Massachusetts Inst. of Technology (US)), viphava khlaisuwan
    10/19/26, 3:30 PM

    CMS Computing Operations runs the experiment's data management and processing on the WLCG. Operators answer a steady stream of questions about Rucio rules, datasets, sites, workflows and the tools behind them, drawing on scattered documentation, code, tickets and live service data. We built an AI assistant for CMS Computing Operations on the Archi framework and deployed it for operators. It...

    Go to contribution page
  8. Dr Giordon Holtsberg Stark (University of Chicago (US))
    10/19/26, 4:15 PM

    Large language model agents are becoming useful for software development and scientific analysis, but making them useful on shared computing infrastructure requires more than the model itself. Agents need reliable access to the software, data, workflows, and identities that researchers already use.

    This talk introduces the Model Context Protocol (MCP) as a practical interface between AI...

    Go to contribution page
  9. Pawel Kopciewicz (CERN)
    10/20/26, 9:00 AM

    The LHCb Brain Knowledge Base is the searchable corpus that grounds LHCb Brain reasoning. CDS documents, GitLab code, merge requests and issues, TWiki, Indico, and LHCb HTML domains are collected by dedicated scrapers running as cron jobs on Kubernetes in the CERN PaaS. For PDF documents, Docling on GPU extracts the text and reconstructs LaTeX formulas. The text is chunked, and a header is...

    Go to contribution page
  10. Jason Oliver (Adelaide University (AU))
    10/20/26, 9:20 AM

    ATLAS OpenSearch meshes over twenty CERN sources — TWiki,
    Zensical/MkDocs, GitLab, Indico, CDS, CDS Videos, arXiv, Inspire,
    JIRA, Confluence, analysis notes, and more — into aliased,
    independently indexed knowledge bases, searchable through the ATLAS
    documentation site and used by over 600 collaboration members. Agent
    and MCP interfaces came later, built on top of that same index.

    Each...

    Go to contribution page
  11. Alex Sopio (The University of Edinburgh (GB)), Daniel Thomas Murnane (Niels Bohr Institute, University of Copenhagen), Gabriel Facini (UCL (GB)), Joe Egan (University College London), Juerg Beringer (Lawrence Berkeley National Laboratory (LBNL)), Ki Ryeong Park (Columbia University (US))
    10/20/26, 9:40 AM

    chATLAS is a deployed Retrieval-Augmented Generation assistant providing source-attributed conversational and search access to more than 30,000 documents from several ATLAS documentation systems. It combines dense and keyword retrieval with domain-adapted embeddings, contextual retrieval, and ranking. A benchmark constructed from ATLAS documentation is used to evaluate retrieval and answer...

    Go to contribution page
  12. Abhishikth Mallampalli (University of Wisconsin (US)), Deborah Pinna (University of Wisconsin (US)), Sridhara Dasu (University of Wisconsin Madison (US)), Tulika Bose (University of Wisconsin (US))
    10/20/26, 10:00 AM

    Information about the CMS physics programme is spread across hundreds of publications and internal analysis notes and is accessible mainly through manual search. We present two synergistic approaches developed at UW–Madison, both running on-premises with open models.

    MITRA is a retrieval-augmented assistant over CMS analysis documentation - internal and public. A two-tier vector database...

    Go to contribution page
  13. Dietrich Liko (Austrian Academy of Sciences (AT)), Dr Ulrich Schwickerath (CERN)
    10/20/26, 11:00 AM

    The DPHEP initiative preserves collider data, but they remain useful only as long as the tacit knowledge surrounding them survives. While the JADE reanalysis succeeded years after PETRA shut down because former collaborators were available to explain the detector, software, and analysis choices, that live expertise is now rapidly disappearing for the LEP experiments.

    As a pilot project, we...

    Go to contribution page
  14. Sokratis Papadopoulos (CERN)
    10/20/26, 11:30 AM

    Behind most knowledge bases and LLM agents there is a retrieval problem: finding the right information quickly, and only what the user is allowed to see. OpenSearch, an open-source (Apache 2.0) search and analytics engine, has grown from a scalable full-text engine into a platform that covers this ground in one place. This talk gives an overview of what OpenSearch offers for knowledge bases...

    Go to contribution page
  15. Anna Hallin (University of Hamburg), Dr Carsten Burgard (Hamburg University (DE)), Gregor Kasieczka (Hamburg University (DE)), Sarah Heim (Deutsches Elektronen-Synchrotron (DE)), Tim Lukas (University of Hamburg)
    10/20/26, 12:00 PM

    Large Language Models (LLMs) and LLM based agentic systems have transformed how work is done in many industries, especially software development and mathematics.
    As physicists we have to ask ourselves how we can benefit from these developments, and what the best use cases are.
    Previous case studies have shown that agents are generally capable of using HEP tooling and supporting...

    Go to contribution page
  16. Benjamin Galewsky (Univ. Illinois at Urbana Champaign (US))
    10/20/26, 12:20 PM

    With version 3 of MLFlow, there is now some significant support for developing agentic applications. It helps with evaluating prompts, skills, models, and MCP servers and helps developers evaluate agent response quality.

    We will describe some of the more important features and show how the Agentic IRIS-HEP project is making use of it.

    Go to contribution page
  17. Aman Desai (Adelaide University (AU))
    10/20/26, 12:40 PM

    We present RooAgent, a Python package that provides an LLM-based interface for ROOT-based high energy physics data analysis. Analysis functions covering histogram inspection, event selection, visualisation of kinematic distributions, fitting, and significance estimation are exposed as tools that an LLM agent invokes, supplying the required arguments in response to plain-language prompts. The...

    Go to contribution page
  18. Noah Julian Stauble (ETH Zurich (CH)), Stefano Marin
    10/20/26, 2:20 PM

    Language models process code as a flat token window, but the information flow of a large codebase is obfuscated from this viewpoint: call structure, control flow, and shared state are graph-shaped and repository-wide. Our project proposes coupling a graph transformer over the property graph of such a codebase to a pretrained decoder LLM. Our target is FLUKA, a general-purpose Monte Carlo code...

    Go to contribution page
  19. Niki Saoulidou (National and Kapodistrian University of Athens (GR))
    10/20/26, 2:40 PM

    The rapid development of knowledge bases and AI agents offers new opportunities within the increasingly complex workflows of experimental particle physics. Their use in physics analyses, however, requires establishing how such systems can be benchmarked, made reproducible and scientifically validated, and how improvements over expert-designed analyses can be understood.
    This contribution...

    Go to contribution page
  20. Alexia Martorell I Granollers (La Salle, Ramon Llull University (ES)), Arantza De Oyanguren Campos (Univ. of Valencia and CSIC (ES)), Carlos Abia Sarria (Univ. of Valencia and CSIC (ES)), Cilicia Uzziel Perez (La Salle, Ramon Llull University (ES)), Miriam Calvo Gomez (La Salle, Ramon Llull University (ES)), Xavier Vilasis Cardona (La Salle, Ramon Llull University (ES))
    10/20/26, 3:00 PM

    We present an update on our prototype Retrieval-Augmented Generation (RAG) and agentic LLM tool designed to accelerate and support high-energy physics analyses. As a case study, we applied the system to the published 2016 Λb → Λγ Run 2 LHCb analysis. Reproducing legacy workflows is often slow and error-prone due to fragmented code, dispersed documentation, personnel turnover, and software...

    Go to contribution page
  21. Andrzej Novak (Massachusetts Inst. of Technology (US)), Dolores Garcia (Massachusetts Inst. of Technology (US)), Eric Anton Moreno (Massachusetts Institute of Technology (US)), Philip Coleman Harris (Massachusetts Inst. of Technology (US)), Samuel Kai Bright-Thonney (Massachusetts Inst. of Technology (US)), Yiyang Zhao (Massachusetts Inst. of Technology (US))
    10/20/26, 3:20 PM

    Experimental high energy physics analysis is traditionally a multi-year effort dominated by repetitive implementation that demands little physics insight. LLM-based AI agents can now autonomously execute substantial portions of this pipeline, collapsing the implementation bottleneck to roughly ten hours of wall-clock time. This talk surveys the rapidly developing landscape of agentic AI in...

    Go to contribution page
  22. Alexander Yue, Julia Lynne Gonski (SLAC National Accelerator Laboratory (US)), Qibin Liu (SLAC National Accelerator Laboratory (US))
    10/20/26, 3:40 PM

    Recent advances in agentic AI have demonstrated the potential to automate complex high-energy physics (HEP) workflows. We focus on the regime of HEP tasks where frontier models still struggle to provide correct and complete solutions, and introduce an open-ended optimization task format with continuous, automatically evaluated rewards. Unlike conventional benchmarks focused on task completion,...

    Go to contribution page
  23. Gabriel Facini (UCL (GB))
    10/20/26, 5:30 PM
  24. Francesco Crescioli (Centre National de la Recherche Scientifique (FR)), Matthias Saimpert (CEA - IRFU - Université Paris-Saclay (FR))
    10/21/26, 9:00 AM

    The ATLAS ITk pixel-module local database ([LocalDB][1]) is a critical MongoDB system that tracks thousands of pixel modules and their components (bare modules, flex PCBs, and frontend chips) throughout complex assembly and testing workflows.

    We have developed and deployed an [agent][2] that enables researchers to query this database in natural language. The agent routes queries through...

    Go to contribution page
  25. Adrien Ledeul (CERN), Alex Savulescu (CERN), David Villamil Fernandez (CERN), Gustavo Segura (CERN)
    10/21/26, 9:30 AM

    Members of CERN's Occupational Health & Safety and Environmental Protection (HSE) Department work with data that is often sensitive, and personal correspondence. General-purpose AI assistants are not an option for this material, because they send it to external providers and give little control over what gets read. Orbit is a desktop application for macOS, Windows and Linux built to close that...

    Go to contribution page
  26. Adrien Ledeul (CERN), Alex Savulescu (CERN), David Villamil Fernandez (CERN), Gustavo Segura (CERN)
    10/21/26, 9:50 AM

    AI conversations often start from scratch. Decisions, corrections and preferences get lost between chats, while a team’s knowledge remains scattered across mailboxes and documents.

    Brains, Orbit’s memory, keeps that knowledge as readable Markdown notes, one per concept. You can organize brains around your own work, a team or a project. Notes link to each other, helping Orbit retrieve...

    Go to contribution page
  27. 10/21/26, 10:10 AM
  28. Aron Soha (Fermi National Accelerator Lab. (US)), Gabriele Benelli (Brown University (US)), Jessica Tang (Brown University (US)), Juan Pablo Salas Galindo (University of Wisconsin (US)), Samantha Andrea Sunnarborg (Brown University)
    10/21/26, 11:00 AM

    Efficient and effective operation and data quality monitoring (DQM) are crucial to the success of high energy physics experiments. These important functionsoften fall to shifters who range from students to experts who work with varied understandings of the complicated subsystems they oversee. Agentic LLM-powered chatbots are particularly well suited for the structure of shift taking as they...

    Go to contribution page
  29. Krittin Phornsiricharoenphant (Chulalongkorn University (TH)), Hsuan-Chi Liu, Vijay Chakravarty (CERN), Katy Ellis (Science and Technology Facilities Council STFC (GB)), Stefano Belforte (Universita e INFN Trieste (IT))
    10/21/26, 11:20 AM

    Archi-CRAB: a knowledge-graph-grounded, tool-integrated assistant for CMS CRAB Analysis user support

    Archi-CRAB is an AI assistant for analysis user support in CRAB, the CMS Remote Analysis Builder. It builds on two open-source projects, OKG, a knowledge-graph engine, and Archi, its OKG distribution for HEP and operational use, taking their CERN-team bundle (connectors, schemas, skills) as...

    Go to contribution page
  30. Alina Corso Radu (University of California Irvine (US)), Antoine Marzin (CERN), Giuseppe Avolio (CERN), Joaquin Hoya (Argonne National Laboratory (US)), Luigi Podda (CERN), Sylvain Chapeland (CERN), Walter Hopkins (Argonne National Laboratory (US))
    10/21/26, 11:40 AM

    EP R&D WP9.1 is a cross-experiment collaboration, and its objective is to investigate the potential of Artificial Intelligence (AI) solutions to improve automation and the overall efficiency of experiment operations. Currently, data-acquisition systems for LHC experiments rely on rule-based expert systems and complex event processing for tasks such as error handling and anomaly detection....

    Go to contribution page
  31. Ilija Vukotic (University of Chicago (US))
    10/21/26, 1:30 PM

    The operational knowledge behind ATLAS distributed computing (how Rucio, PanDA, FTS, CRIC and the sites behave, and why) is spread across TWiki pages, GitHub, Indico slides, GGUS tickets, mailing lists and people's heads. Much of it contradicts itself or is out of date. ChATLAS, an ATLAS project, answers questions by retrieval-augmented generation over such documents. OWL complements it by...

    Go to contribution page
  32. Guillermo Loustau De Linares (University of Massachusetts (US))
    10/21/26, 2:00 PM

    codefactory is designed to reduce the time spent reconstructing context, locating authoritative sources, and setting up tools when moving between repositories. The goal is practical: make engineering work more efficient without allowing a coding agent to decide what it may change or whether a result is correct. \codefactory separates orchestration, context and evidence, reusable...

    Go to contribution page
  33. Alexandre Franck Boyer (CERN), Ryunosuke O'Neil (CERN), The LHCb Brain
    10/21/26, 2:20 PM

    The LHCb Brain Agents (LbAgents) is the set of AI agents that assist LHCb physicists and operators with the experiment's computing systems. The first use case targets Analysis Productions, where physicists request the processing of data and simulation by opening a GitLab merge request, and a CI pipeline runs test jobs on the grid before the production is submitted. When the pipeline fails,...

    Go to contribution page
  34. Sreevani Jarugula (Fermi National Accelerator Lab. (US))
    10/21/26, 3:10 PM

    The Compact Muon Solenoid (CMS) experiment at the Large Hadron Collider generates a large volume of complex data, making manual inspection of Data Quality Monitoring (DQM) plots by shift takers increasingly difficult. Agentic AI systems built on vision-language models (VLMs) are rapidly being developed to address this, as they can interpret DQM plots against shift instructions and deliver...

    Go to contribution page
  35. 10/21/26, 3:30 PM

    The Geodetic Metrology (BE-GM) group manages more than a decade of operational knowledge scattered across heterogeneous storage systems: JIRA for day-to-day survey tickets, Confluence for policies and standard procedures, GitLab for software and infrastructure-as-code, MkDocs sites for the user-facing manuals of in-house tooling such as LGC2, and shared file stores holding survey reports,...

    Go to contribution page
  36. 10/22/26, 2:00 PM
  37. 10/22/26, 4:00 PM
  38. 10/22/26, 5:30 PM
  39. Adrian Wuthrich, Arno Simons, Dalal El Youssoufi, Michael Zichert
    10/23/26, 9:00 AM

    We will present our “Network Epistemology in Practice” project, an initiative to capture knowledge generation processes in large-scale science collaborations and to analyze them from philosophical, historical and sociological perspectives. The project is funded by the European Research Council and works under a Short Term Association with ATLAS. In the project, we will use network analysis and...

    Go to contribution page
  40. Laurent Bindschaedler (Max Planck Institute for Software Systems)
    10/23/26, 9:30 AM
    1

    Agents are moving from answering questions about infrastructure to operating it, for example by restarting services or resubmitting jobs. This shift makes mistakes costly: once an agent runs commands itself, one wrong step can cause damage that is hard to undo, which an agent caught in a retry loop may repeat many times. Existing safeguards do not prevent this. Prompts and command allowlists...

    Go to contribution page
  41. Jason Oliver (Adelaide University (AU))
    10/23/26, 10:40 AM
  42. Christoph Paus (Massachusetts Inst. of Technology (US))
    10/23/26, 11:20 AM
  43. Lukas Alexander Heinrich (Technische Universitat Munchen (DE))
    10/23/26, 12:00 PM
  44. The COSINUS collaboration is preparing for its first dark matter data-taking run. As the experiment moves toward data collection, we are exploring how AI agents could support the collaboration’s scientific and operational workflows. As a CERN-affiliated experiment, we would like to discuss what agent infrastructure or services CERN plans to provide, as these could be an ideal foundation for...

    Go to contribution page
  45. CMS physics knowledge lives across many analysis notes, publications, twikis, gitlabs, etc., and is not easy or convenient to query, for humans or agents. We have put together an initial version of an operational knowledge graph (OKG) with these sources. We hope to lower the barrier for CMS members to more easily implement specific recipes, see how other analyses solved problems that recur...

    Go to contribution page
  46. Jason Mohoney (Massachusetts Inst. of Technology (US))

    Scientific computing facilities scatter operational knowledge across uncoordinated sources: technical documentation, code repositories, internal notes, ticket histories, and diagnostic logs. In production for the CMS experiment at CERN, our assistant Archi has supported computing operations since February 2026, querying such corpora alongside live monitoring feeds. Text retrieval makes these...

    Go to contribution page