Open Access
- 25 March 2026
- journal article
- Published by Stichting SciPost in SciPost Physics
- Vol. 20 (3)
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.Keywords
Funding Information
- Deutsche Forschungsgemeinschaft (390833306)
- Deutsche Forschungsgemeinschaft (460248186)
- Deutsche Forschungsgemeinschaft (EXC-2094-390783311)
- Deutsche Forschungsgemeinschaft (396021762 — TRR 257)
- U.S. Department of Energy (DE-AC02- 05CH11231)
This publication has 77 references indexed in Scilit:
- Augmenting large language models with chemistry toolsNature Machine Intelligence, 2024
- Machine learning for anomaly detection in particle physicsReviews in Physics, 2024
- Autonomous chemical research with large language modelsNature, 2023
- Machine learning in the search for new fundamental physicsNature Reviews Physics, 2022
- Odd dimensional analogue of the Euler characteristicJournal of High Energy Physics, 2021
- Array programming with NumPyNature, 2020
- SciPy 1.0: fundamental algorithms for scientific computing in PythonNature Methods, 2020
- Classification without labels: learning from mixed samples in high energy physicsJournal of High Energy Physics, 2017
- Maximizing boosted top identification by minimizing N-subjettinessJournal of High Energy Physics, 2012
- Identifying boosted objects with N-subjettinessJournal of High Energy Physics, 2011