-
Sergio Arguedas Cuendis (CONARE)27/08/2026, 14:00Agentic AI
The LHCb collaboration at CERN spans from individual physics analyses to production computing. That breadth makes it a natural place for the agentic AI. The software stack grew over decades around human experts. The physics is split into internal working groups, which standard LLMs were not trained to distinguish. This HEP-specific workflow cannot be integrated with commercial tools without...
Go to contribution page -
Daniel Schiller (Institute for Theoretical Physics, Heidelberg University)27/08/2026, 14:10Agentic AI
We present MadAgents, an effective and communicative set of agents for working with MadGraph. Agentic installation, learning-by-doing training, user support, and autonomous simulation campaigns provide easy access to state-of-the-art simulations and accelerate LHC research. We show how MadAgents interact with inexperienced and advanced users, support a range of simulation tasks, and analyze...
Go to contribution page -
Nikita Schmal (ITP, Heidelberg University)27/08/2026, 14:20Agentic AI
Analysis re-casting at the LHC is highly standardized and nevertheless requires resources, time, and expert physics input. Building on the newly developed MadAgents.v3 framework, we demonstrate how a global SMEFT analysis can be updated through an agentic workflow with a physicist in the loop. Although demonstrated within the SFitter framework, the underlying technical aspects of the agentic...
Go to contribution page -
Andrew Pilkington (University of Manchester)27/08/2026, 14:30Agentic AI
Particle physics collider experiments provide Rivet routines as part of the analysis preservation strategy for model-independent measurements. Rivet is a C++ toolkit that allow new theoretical models to be compared to the measurements, thus aiding the development and tuning of Monte Carlo event generators as well as searches for physics beyond the Standard Model. However, analysis coverage is...
Go to contribution page -
Alexander Kazatsky (Ruhr University Bochum)27/08/2026, 14:50Agentic AI
Natural science increasingly relies on complex models embedded in large computational frameworks. Motivated by the DEMOS (DEmocratizing MOdelS) project's goal of making research models interoperable and encoding them into framework-independent formats, we address a necessary prerequisite: reconstructing an analysis-specific model and translating it between frameworks without changing its...
Go to contribution page -
Aleksei Mikhasenko (Universität Bonn)27/08/2026, 15:00Agentic AI
Across many fields of fundamental physics, researchers must reason over large and growing corpora of specialized publications and increasingly turn to language models for help — yet these models rarely connect their answers to the primary sources they draw on and often lack the information to give a reliable answer. Building on the PathRAG graph-retrieval framework, we adapt it to...
Go to contribution page -
Gianluca Inguglia (MBI Vienna)27/08/2026, 15:10Agentic AI
We present a first head-to-head comparison of different agentic AI systems applied to the study of gravitational waves. Agentic systems, supervised either via a human-in-the-loop or in fully autonomous mode, are tasked with performing matched-filter analyses in the context of the Einstein Telescope mock data challenge and with fully writing a scientific paper in the style of PRD. While all...
Go to contribution page -
Shivam Rawat (University of Bonnn)27/08/2026, 15:20Agentic AI
Agentic AI systems are increasingly deployed in scientific workflows, yet existing evaluations primarily measure task completion and provide limited insight into scientific reliability. We argue that such metrics are insufficient for assessing autonomous systems in research settings, where plausible but incorrect results may be more dangerous than overt failures.
We present a structured...
Go to contribution page
Choose timezone
Your profile timezone: