Reining in an Agentic Harness for High Energy Physics
Abstract
Agentic systems now address tasks across theoretical, phenomenological, and experimental high energy physics (HEP), but their scientific capabilities remain difficult to reuse across different large language models, providers, and harnesses. We argue that stable parts of these workflows should be promoted into versioned scientific operations and exposed through common protocols. Existing general-purpose harnesses can then be specialized for HEP through task-specific sets of tools and skills, while community-maintained registries would make these capabilities discoverable and citable. We identify mismatches in conventions, assumptions, and domains of validity among independently developed operations as a potential obstacle to their composition, and discuss machine-readable scientific contracts as one possible solution. These design principles and evaluation guidelines provide a near-term path toward a portable and community-maintained agentic harness for HEP.
Related
- HEPTABench: A framework for portable and controlled agentic evaluations in high energy physics
- Young Gerard storming high energy physics
- The method of kinematic limits in high-energy physics
- Promoting Green Computing in High Energy Physics and Astrophysics
- SuperJEPA: Pretraining with a Supervision-Augmented Joint-Embedding Predictive Architecture for High Energy Physics
BibTeX
@misc{menzo2026reining,
title = {{Reining in an Agentic Harness for High Energy Physics}},
author = {Tony Menzo and George T. Fleming and Konstantin T. Matchev and Stephen Mrenna and Alexander Roman},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.00107},
eprint = {2609.00107},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.00107},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Reining in an Agentic Harness for High Energy Physics
AU - Tony Menzo
AU - George T. Fleming
AU - Konstantin T. Matchev
AU - Stephen Mrenna
AU - Alexander Roman
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2609.00107
UR - https://arxiv.org/abs/2609.00107
AB - Agentic systems now address tasks across theoretical, phenomenological, and experimental high energy physics (HEP), but their scientific capabilities remain difficult to reuse across different large language models, providers, and harnesses. We argue that stable parts of these workflows should be promoted into versioned scientific operations and exposed through common protocols. Existing general-purpose harnesses can then be specialized for HEP through task-specific sets of tools and skills, while community-maintained registries would make these capabilities discoverable and citable. We identify mismatches in conventions, assumptions, and domains of validity among independently developed operations as a potential obstacle to their composition, and discuss machine-readable scientific contracts as one possible solution. These design principles and evaluation guidelines provide a near-term path toward a portable and community-maintained agentic harness for HEP.
ER -