Noah Clarke Hall, Ioannis Xiotidis, Nikos Konstantinidis
et al.
High-energy physics experiments face extreme data rates, requiring real-time trigger systems to reduce event throughput while preserving sensitivity to rare processes. Trigger systems are typically constructed as modular chains of sequentially optimised algorithms, including machine learning models. Each algorithm is optimised for a specific local objective with no guarantee of overall optimality. We instead formulate trigger design as a constrained end-to-end optimisation problem, treating all stages- including data encoding, denoising, clustering, and calibration- as components of a single differentiable system trained against a unified physics objective. The framework jointly optimises performance while incorporating physics and deployment constraints. We demonstrate this approach on a hardware multi-jet trigger inspired by the ATLAS High-Luminosity Large Hadron Collider design. Using Higgs boson pair production as a benchmark, we observe x2-4 improvement in true-positive rate at fixed false-positive rate, while preserving interpretable intermediate physics objects and monotonic calibration constraints. These results highlight end-to-end optimisation as a practical paradigm for next-generation real-time event selection systems.
Detector visualization plays a vital role in high energy physics (HEP) experiments, yet existing detector descriptions, such as GDML, lack compatibility with industrial 3D tools. We present an automated conversion framework that transforms four major HEP detector descriptions, including GDML, Geant4, ROOT and DD4hep, into standardized FBX models compatible with a industrial 3D platform called Unity. This solution enables HEP detectors to be directly visualized in the professional 3D ecosystem, which is of great help for detector design verification, event display development, and public participation.
Tony Menzo, Alexander Roman, Sergei Gleyzer
et al.
Many workflows in high-energy-physics (HEP) stand to benefit from recent advances in transformer-based large language models (LLMs). While early applications of LLMs focused on text generation and code completion, modern LLMs now support orchestrated agency: the coordinated execution of complex, multi-step tasks through tool use, structured context, and iterative reasoning. We introduce the HEP Toolkit for Agentic Planning, Orchestration, and Deployment (HEPTAPOD), an orchestration framework designed to bring this emerging paradigm to HEP pipelines. The framework enables LLMs to interface with domain-specific tools, construct and manage simulation workflows, and assist in common utility and data analysis tasks through schema-validated operations and run-card-driven configuration. To demonstrate these capabilities, we consider a representative Beyond the Standard Model (BSM) Monte Carlo validation pipeline that spans model generation, event simulation, and downstream analysis within a unified, reproducible workflow. HEPTAPOD provides a structured and auditable layer between human researchers, LLMs, and computational infrastructure, establishing a foundation for transparent, human-in-the-loop systems.
Solar neutrino flux constraints from the legacy GALLEX/GNO and SAGE experiments continue to influence contemporary global analyses of neutrino properties. The constraints depend on the neutrino absorption cross sections for various solar sources. Following recent work updating the $^{51}$Cr and $^{37}$Ar neutrino source cross sections, we reevaluate the $^{71}$Ga solar neutrino cross sections, focusing on contributions from transitions to $^{71}$Ge excited states, but also revising the ground-state transition to take into account new $^{71}$Ge electron-capture lifetime measurements and various theory corrections. The excited-state contributions have been traditionally taken from forward-angle $(p,n)$ cross sections. Here we correct this procedure for the $\approx 10\%-20\%$ tensor operator contribution that alters the relationship between Gamow-Teller and $(p,n)$ transition strengths. Using state-of-the-art nuclear shell-model calculations to evaluate this correction, we find that it lowers the $^8$B and hep neutrino cross sections. However, the addition of other corrections, including contributions from near-threshold continuum states that radiatively decay, leads to an overall increase in the $^8$B and hep cross sections of $\approx 10\%$ relative to the values recommended by Bahcall. Uncertainties are propagated using Monte Carlo simulations.
The Higgs boson, discovered back in 2012 through collision data at the Large Hadron Collider (LHC) by ATLAS and CMS experiments, marked a significant inflection point in High Energy Physics (HEP). Today, it's crucial to precisely measure Higgs production processes with LHC experiments in order to gain insights into the universe and find any invisible physics. To analyze the vast data that LHC experiments generate, classical machine learning has become an invaluable tool. However, classical classifiers often struggle with detecting higgs production processes, leading to incorrect labeling of Higgs Bosons. This paper aims to tackle this classification problem by investigating the use of quantum machine learning (QML).
Large Language Models (LLMs) are undergoing a period of rapid updates and changes, with state-of-the-art (SOTA) model frequently being replaced. When applying LLMs to a specific scientific field, it's challenging to acquire unique domain knowledge while keeping the model itself advanced. To address this challenge, a sophisticated large language model system named as Xiwu has been developed, allowing you switch between the most advanced foundation models and quickly teach the model domain knowledge. In this work, we will report on the best practices for applying LLMs in the field of high-energy physics (HEP), including: a seed fission technology is proposed and some data collection and cleaning tools are developed to quickly obtain domain AI-Ready dataset; a just-in-time learning system is implemented based on the vector store technology; an on-the-fly fine-tuning system has been developed to facilitate rapid training under a specified foundation model. The results show that Xiwu can smoothly switch between foundation models such as LLaMA, Vicuna, ChatGLM and Grok-1. The trained Xiwu model is significantly outperformed the benchmark model on the HEP knowledge question-and-answering and code generation. This strategy significantly enhances the potential for growth of our model's performance, with the hope of surpassing GPT-4 as it evolves with the development of open-source models. This work provides a customized LLM for the field of HEP, while also offering references for applying LLM to other fields, the corresponding codes are available on Github.
Recently, Kolmogorov-Arnold Networks (KANs) have been proposed as an alternative to multilayer perceptrons, suggesting advantages in performance and interpretability. We study a typical binary event classification task in high-energy physics including high-level features and comment on the performance and interpretability of KANs in this context. Consistent with expectations, we find that the learned activation functions of a one-layer KAN resemble the univariate log-likelihood ratios of the respective input features. In deeper KANs, the activations in the first layer differ from those in the one-layer KAN, which indicates that the deeper KANs learn more complex representations of the data, a pattern commonly observed in other deep-learning architectures. We study KANs with different depths and widths and we compare them to multilayer perceptrons in terms of performance and number of trainable parameters. For the chosen classification task, we do not find that KANs are more parameter efficient. However, small KANs may offer advantages in terms of interpretability that come at the cost of only a moderate loss in performance.