Towards AI-Agent-Accelerated Research in High-Energy Physics: A Case Study in Monte Carlo Analysis
Abstract
We investigate how far contemporary LLM-based agents can participate in multistep computational high-energy-physics research under reproducible human supervision. Using a previously published CEPC Bell-observable analysis in e+e- → ZH, Z → qq̅, H → ZZ* → 4μ as a case study, we test two capabilities. First, the agent performs an instruction-constrained reproduction: it is explicitly instructed not to use the published numerical results as analysis targets, although no technical information-access barrier is imposed. The analysis definition is fixed before the formal comparison, and the resulting detector-level I3 central values reproduce the four published benchmark points to within about 2% without retuning to those values. Second, the agent is used for an open-ended extension with no target answer supplied. Using 200,000 fast-simulated events, a stage-resolved audit identifies muon isolation as the largest single contribution to the hard-to-detector shift, and subsequent diagnostics connect the effect to angle-dependent isolation efficiency, proximity to the hard Z → qq̅ system, and mixed electromagnetic activity from muon final-state radiation and hadron decays. Throughout, the agent assists with workflow planning, code and configuration inspection, Monte Carlo production, anomaly diagnosis, control construction, statistical analysis, and result organization, while state-changing actions and final interpretation remain under human control. The study shows that the value of AI agents in HEP may lie not only in faster code generation, but in faster scientific iteration, and motivates systematic benchmarking across historical HEP analyses using correctness, human intervention, and researcher-time efficiency as explicit metrics.
Related
- EasyScan_HEP 2: LLM-Agent Parameter-Scan Workflows in High Energy Physics
- FUSION: a skill-based research agent for publicly obtainable nuclear-physics codes
- Vectorized Symmetric and Fermionic Tensor Network Implementations for GPU-Accelerated Variational Monte Carlo
- Passage of particles through matter and the effective straggling-function: High-fidelity accelerated simulation via Physics-Informed Machine Learning
- ColPackAgent: Agent-Skill-Guided Hard-Particle Monte Carlo Workflows for Colloidal Packing
BibTeX
@misc{gao2026towards,
title = {{Towards AI-Agent-Accelerated Research in High-Energy Physics: A Case Study in Monte Carlo Analysis}},
author = {Tianqi Gao and Ruobing Jiang},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.03373},
eprint = {2611.03373},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.03373},
}
RIS
TY - UNPB
TI - Towards AI-Agent-Accelerated Research in High-Energy Physics: A Case Study in Monte Carlo Analysis
AU - Tianqi Gao
AU - Ruobing Jiang
PY - 2026
DA - 2026/11/02
PB - arXiv
DO - 10.48550/arxiv.2611.03373
UR - https://arxiv.org/abs/2611.03373
AB - We investigate how far contemporary LLM-based agents can participate in multistep computational high-energy-physics research under reproducible human supervision. Using a previously published CEPC Bell-observable analysis in e^+e^- → ZH, Z → qq̅, H → ZZ^* → 4μ as a case study, we test two capabilities. First, the agent performs an instruction-constrained reproduction: it is explicitly instructed not to use the published numerical results as analysis targets, although no technical information-access barrier is imposed. The analysis definition is fixed before the formal comparison, and the resulting detector-level I_3 central values reproduce the four published benchmark points to within about 2% without retuning to those values. Second, the agent is used for an open-ended extension with no target answer supplied. Using 200,000 fast-simulated events, a stage-resolved audit identifies muon isolation as the largest single contribution to the hard-to-detector shift, and subsequent diagnostics connect the effect to angle-dependent isolation efficiency, proximity to the hard Z → qq̅ system, and mixed electromagnetic activity from muon final-state radiation and hadron decays. Throughout, the agent assists with workflow planning, code and configuration inspection, Monte Carlo production, anomaly diagnosis, control construction, statistical analysis, and result organization, while state-changing actions and final interpretation remain under human control. The study shows that the value of AI agents in HEP may lie not only in faster code generation, but in faster scientific iteration, and motivates systematic benchmarking across historical HEP analyses using correctness, human intervention, and researcher-time efficiency as explicit metrics.
ER -