Agents of discovery
SciPost Physics, vol. 20
Abstract
The substantial data volumes encountered in modern particle physics and other domains of fundamental physics research allow (and require) the use of increasingly complex data analysis tools and workflows. While the use of machine learning (ML) tools for data analysis has recently proliferated, these tools are typically special-purpose algorithms that rely, for example, on encoded physics knowledge to reach optimal performance. In this work, we investigate a new and orthogonal direction: Using recent progress in large language models (LLMs) to create a team of agents — instances of LLMs with specific subtasks — that jointly solve data analysis-based research problems in a way similar to how a human researcher might: by creating code to operate standard tools and libraries (including ML systems) and by building on results of previous iterations. If successful, such agent-based systems could be deployed to automate routine analysis components to counteract the increasing complexity of modern tool chains. To investigate the capabilities of current-generation commercial LLMs, we consider the task of anomaly detection via the publicly available and highly-studied LHC Olympics dataset. Several current models by OpenAI (GPT-4o, o4-mini, GPT-4.1, and GPT-5) are investigated and their stability tested. Overall, we observe the capacity of the agent-based system to solve this data analysis problem. The best agent-created solutions mirror the performance of human state-of-the-art results.
Authors 5
-
Lawrence Berkeley National Laboratory
Affiliation as printed
Lawrence Berkeley National Laboratory
-
Affiliation as printed
University of Hamburg
-
Affiliation as printed
University of Hamburg
-
Michael Krämer Aachen
Affiliation as printed
RWTH Aachen University
-
Affiliation as printed
University of Hamburg
Cited by 1 stored of 1
1 result
No patents citing this paper on Lens.org (checked 2026-10-06).