Erlangen 2026 – scientific programme
Parts | Days | Selection | Search | Updates | Downloads | Help
T: Fachverband Teilchenphysik
T 56: Data, AI, Computing, Electronics VI
T 56.5: Talk
Wednesday, March 18, 2026, 17:15–17:30, KH 02.014
Agents of Discovery — Sascha Diefenbacher1, Anna Hallin2, Gregor Kasieczka1, Michael Krämer1, Anne Lauscher3, and •Tim Lukas1 — 1University of Hamburg, Hamburg, Germany — 2Lawrence Berkeley National Laboratory, Berkley, USA — 3RWTH Aachen University, Aachen, Germany
Particle physics is becoming more and more data intensive, requiring increasingly complex analysis methods. Large parts of these methods belong to standard procedures which have to be implemented by hand, taking time away from more innovative work. With the rise of agentic AI systems other approaches become feasible: Tasking AI agents with implementing those known parts, making workflows more efficient.
In this work we present a framework allowing a team of AI Agents to work autonomously on a given task, including capabilities for writing code, code execution, error correction and logic checks. The setup uses state-of-the art OpenAI LLMs and has been tested in the realm of anomaly detection. The performance was monitored throughout many different technical and physical metrics, allowing us to draw detailed conclusions on the capabilities of the different LLMs: Most are capable of solving the given task, while the best were able to match human level performance.
Keywords: AI agents; LLM; anomaly detection; particle physics