Back to Conference View
Login

Agentic AI for Particle Physics Mini-Workshop @ ETHZ

→ Europe/Zurich
Siemens Auditorium, HIT (ETH Zürich Hönggerberg)

Siemens Auditorium, HIT

ETH Zürich Hönggerberg
Daniel Thomas Murnane (Niels Bohr Institute, University of Copenhagen), Eric Anton Moreno (Massachusetts Institute of Technology (US)), Thea Aarrestad (ETH Zurich (CH))
Description

"English is the new coding language"

AI agents make it possible to automate substantial parts of scientific workflows. They can support end-to-end research processes, including (but not limited do) literature review, analysis planning, code development, statistical inference, documentation, and scientific reporting.

In this mini-workshop, we demonstrate practical agentic workflows for scientific research and discuss how these tools can be deployed responsibly and effectively, taking examples from high energy physics. We discuss human-in-the-loop approaches, validation strategies, reproducibility, and the evolving role of scientific expertise in the age of increasingly capable AI systems.

Talks and hands-on demonstrations will be followed by an extended discussion and Q&A session amongst all participants (hopefully ranging from undergrad students to full professors), where we discuss:

  • How to use agentic AI to reduce growing coding and workflow burdens in science?
  • What technical skills remain essential for researchers supervising and validating AI-assisted work? 
  • How should research groups, training programs, and scientific collaborations adapt to new capabilities?
  • Best practices to ensure robustness, reproducibility, and scientific accountability?
  • +++

 

We hope to use this as an opportunity to get everyone at the same table and discuss how our communities can most effectively benefit from these technologies while maintaining the high standards of rigor scientific research requires.

Speakers:

Daniel Murnane (Niels Bohr Institute)
Eric Moreno (MIT)
Fazl Barez (University of Oxford/Martian)
Sofia P. Schweizer (Rutgers University)

Papers:
"AI Agents Can Already Autonomously Perform Experimental High Energy Physics" https://arxiv.org/pdf/2603.20179
"Automated Interpretability-Driven Model Auditing and Control: A Research Agenda" F. Barez 
"COLLIDER-BENCH: Benchmarking AI Agents with Particle Physics Analysis Reproduction" arxiv 2605.13950

Agentic AI for Particle Physics Mini-Workshop @ ETHZ
Zoom Meeting ID
65225762608
Host
Thea Aarrestad
Passcode
92573112
Useful links
Join via phone
Zoom URL
    • 1
      Welcome
      Speaker: Thea Aarrestad (ETH Zurich (CH))
      ETHZ_Agentic_AI_Workshop_Intro.pdf
      ETHZ_Agentic_AI_Workshop_Intro.pptx
    • 2
      Agentic workflows in particle physics
      Speaker: Daniel Thomas Murnane (Niels Bohr Institute, University of Copenhagen)
      Slides (in browser)
      video1057571549.mp4
    • 3
      Automated Interpretability for AI Safety
      Speaker: Fazl Barez (University of Oxford)
    • 14:35
      Break
    • 4
      From Prompt to Paper: Tutorial on Agentic Workflows for HEP Data Analysis
      Speaker: Eric Anton Moreno (Massachusetts Institute of Technology (US))
      AIAgents_EricMoreno.pdf
      video2057571549.mp4
    • 5
      COLLIDER-BENCH: Benchmarking AI Agents with Particle Physics Analysis Reproduction
      Speakers: Sofia Palacios Schweitzer (ITP, University Heidelberg), Sofia Palacios Schweitzer
      ETHZ--2026.pdf
    • 6
      Discussion: "English is the new coding language"