AgentRivet: an automated system for producing Rivet routines from journal publications
Abstract
Particle physics collider experiments provide Rivet routines as part of the analysis preservation strategy for model-independent measurements. Rivet is a C++ toolkit that allow new theoretical models to be compared to the measurements, thus aiding the development and tuning of Monte Carlo event generators as well as searches for physics beyond the Standard Model. However, analysis coverage is known to be incomplete, with only 39% of measurements having documented and publicly available Rivet routines. In this article, we design and implement an automated workflow based on Large Language Models with the goal of providing the missing routines. This multi-step workflow, referred to as AgentRivet, extracts the physics analysis information from published papers and writes the missing Rivet routines, with intermediate code- and physics- reviews as part of an autonomous quality control. We report the results obtained using commercial Large Language Models, provided by OpenAI, Anthropic, and Google, for two recent measurements from the ATLAS and CMS experiments. We find that AgentRivet produces competent Rivet routines with few syntax errors. The physics fidelity of the routines is reasonable and follows the explanations given in the relevant publications. Nevertheless, physics-implementation issues do arise and are investigated using the artefacts produced by AgentRivet. The majority of physics implementation issues arise from subtle-but-ambiguous definitions in the given publication, although some models struggle to implement complex observables even when clear definitions are given.
Related
- OperatorToC++: Transpiling Matched EFT Coefficients to Low-Level Routines
- Developing Multi-Dimensional, Sequential sWeighting Routines for Reaction Selection with Emphasis on Kaon Identification at CLAS12
- Equations of motion for dust particles in dust-collecting devices (Translated article from USSR Journal Otoplenie i Ventilyatsiya, No. 4 (1934): 27-29)
- Influence of Ideal, Cubic, and Multiparameter Helmholtz Equations of State on the Static and Dynamic Performance of Porous Aerostatic Journal Bearings
- Trends, Impact, and Thematic Evolution of Physics Education: A Bibliometric and Topic Modelling Analysis of Six Decades of Publications
BibTeX
@misc{costa2026agentrivet,
title = {{AgentRivet: an automated system for producing Rivet routines from journal publications}},
author = {Antonio J. Costa and Caterina Doglioni and Christian Gütschow and Andrew D. Pilkington and Sukanya Sinha},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2606.13535},
eprint = {2606.13535},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.13535},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - AgentRivet: an automated system for producing Rivet routines from journal publications
AU - Antonio J. Costa
AU - Caterina Doglioni
AU - Christian Gütschow
AU - Andrew D. Pilkington
AU - Sukanya Sinha
PY - 2026
DA - 2026/10/16
PB - arXiv
DO - 10.48550/arxiv.2606.13535
UR - https://arxiv.org/abs/2606.13535
AB - Particle physics collider experiments provide Rivet routines as part of the analysis preservation strategy for model-independent measurements. Rivet is a C++ toolkit that allow new theoretical models to be compared to the measurements, thus aiding the development and tuning of Monte Carlo event generators as well as searches for physics beyond the Standard Model. However, analysis coverage is known to be incomplete, with only 39% of measurements having documented and publicly available Rivet routines. In this article, we design and implement an automated workflow based on Large Language Models with the goal of providing the missing routines. This multi-step workflow, referred to as AgentRivet, extracts the physics analysis information from published papers and writes the missing Rivet routines, with intermediate code- and physics- reviews as part of an autonomous quality control. We report the results obtained using commercial Large Language Models, provided by OpenAI, Anthropic, and Google, for two recent measurements from the ATLAS and CMS experiments. We find that AgentRivet produces competent Rivet routines with few syntax errors. The physics fidelity of the routines is reasonable and follows the explanations given in the relevant publications. Nevertheless, physics-implementation issues do arise and are investigated using the artefacts produced by AgentRivet. The majority of physics implementation issues arise from subtle-but-ambiguous definitions in the given publication, although some models struggle to implement complex observables even when clear definitions are given.
ER -