EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Agents of discovery

Sascha Diefenbacher, Anna Hallin, Gregor Kasieczka, Michael Krämer, Anne Lauscher, Tim Lukas

SciPost Physics · 25.03.2026 · 20 (3)

DOI: 10.21468/scipostphys.20.3.091 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SciPost Physics, online erschienen am 25.03.2026. Verfasst von Sascha Diefenbacher und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deutsche Forschungsgemeinschaft, United States Department of Energy.

AbstractBibliografische AngabenZitieren

Abstract (Originalsprache)

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.

Förderung

  • Deutsche Forschungsgemeinschaft
  • United States Department of Energy

Zitieren

APA

Diefenbacher, S., Hallin, A., Kasieczka, G., Krämer, M., Lauscher, A., & Lukas, T. (2026). Agents of discovery. SciPost Physics, 20(3). https://doi.org/10.21468/scipostphys.20.3.091

Vancouver

Diefenbacher S, Hallin A, Kasieczka G, Krämer M, Lauscher A, Lukas T. Agents of discovery. SciPost Physics. 2026;20(3). doi:10.21468/scipostphys.20.3.091

BibTeX
@article{Diefenbacher2026,
  author = {Diefenbacher, Sascha and Hallin, Anna and Kasieczka, Gregor and Krämer, Michael and Lauscher, Anne and Lukas, Tim},
  title = {Agents of discovery},
  journal = {SciPost Physics},
  year = {2026},
  volume = {20},
  number = {3},
  doi = {10.21468/scipostphys.20.3.091}
}
Kostenlos starten →