MadAgents
SciPost Physics Codebases · 2026-11-05
DOI: 10.21468/scipostphyscodeb.86 ↗At a glance
Journal article in SciPost Physics Codebases, published online on 2026-11-05. Written by Tilman Plehn and 2 co-authors. Cited 1 times so far (Crossref); 101 references. The full text is freely available (open access, CC BY 4.0). Funded by: Deutsche Forschungsgemeinschaft, HORIZON EUROPE Framework Programme, HORIZON EUROPE Marie Sklodowska-Curie Actions.
Abstract (original language)
We uncover an effective and communicative set of agents working with MadGraph. Agentic installation, learning-by-doing training, and user support provide easy access to state-of-the-art simulations and accelerate LHC research. We show in detail how MadAgents interact with inexperienced and advanced users, support a range of simulation tasks, and analyze the results. In a second step, we illustrate how MadAgents automatize event generation and run an autonomous simulation campaign, starting from a pdf file of a paper. We also present successive MadAgents updates, including a Claude Code implementation with a self-improvement loop.
Funding
- Deutsche Forschungsgemeinschaft
- HORIZON EUROPE Framework Programme
- HORIZON EUROPE Marie Sklodowska-Curie Actions
Cite
APA
Plehn, T., Schiller, D., & Schmal, N. (2026). MadAgents. SciPost Physics Codebases. https://doi.org/10.21468/scipostphyscodeb.86
Vancouver
Plehn T, Schiller D, Schmal N. MadAgents. SciPost Physics Codebases. 2026. doi:10.21468/scipostphyscodeb.86
BibTeX
@article{Plehn2026,
author = {Plehn, Tilman and Schiller, Daniel and Schmal, Nikita},
title = {MadAgents},
journal = {SciPost Physics Codebases},
year = {2026},
doi = {10.21468/scipostphyscodeb.86}
}
EUVIMED