We present a proof-of-principle study demonstrating the use of large language model (LLM) agents to automate a representative high energy physics (HEP) analysis. Using the Higgs boson diphoton cross-section measurement as a case study with ATLAS Open Data, we design a hybrid system that combines an LLM-based supervisor-coder agent with the Snakemake workflow manager. In this architecture, the workflow manager enforces reproducibility and determinism, while the agent autonomously generates, executes, and iteratively corrects analysis code in response to user instructions. We define quantitative evaluation metrics including success rate, error distribution, costs per specific task, and average number of API calls, to assess agent performance across multi-stage workflows. To characterize variability across architectures, we benchmark a representative selection of state-of-the-art LLMs spanning the Gemini and GPT-5 series, the Claude family, and leading open-weight models. While the workflow manager ensures deterministic execution of all analysis steps, the final outputs still show stochastic variation. Although we set the temperature to zero, other sampling parameters (e.g., top-p, top-k) remained at their defaults, and some reasoning-oriented models internally adjust these settings. Consequently, the models do not produce fully deterministic results. This study establishes the first LLM-agent-driven automated data-analysis framework in HEP, enabling systematic benchmarking of model capabilities, stability, and limitations in real-world scientific computing environments. The baseline code used in this work is available at https://huggingface.co/HWresearch/LLM4HEP. This work was accepted as a poster at the Machine Learning and the Physical Sciences (ML4PS) workshop at NeurIPS 2025. The initial submission was made on August 30, 2025.

Neutral atom quantum computers hold promise for scaling up to hundreds of thousands or more qubits, but their progress is constrained by slow qubit readout. Parallel measurement of qubit arrays currently takes milliseconds, much longer than the underlying quantum gate operations-making readout the primary bottleneck in deploying quantum error correction. Because each round of QEC depends on measurement, long readout times increase cycle duration and slow down program execution. Reducing the readout duration speeds up cycles and reduces decoherence errors that accumulate while qubits idle, but it also lowers the number of collected photons, making measurements noisier and more error-prone. This tradeoff leaves neutral atom systems stuck between slow but accurate readout and fast but unreliable readout. We show that image denoising can resolve this tension. Our framework, GANDALF, uses explicit denoising using image translation to reconstruct clear signals from short, low-photon measurements, enabling reliable classification at up to 1.6x shorter readout times. Combined with lightweight classifiers and a pipelined readout design, our approach both reduces logical error rate by up to 35x and overall QEC cycle time up to 1.77x compared to state-of-the-art convolutional neural network (CNN)-based readout for Cesium (Cs) Neutral Atom arrays.

The physics programs of current and future collider experiments necessitate the development of surrogate simulators for calorimeter showers. While much progress has been made in the development of generative models for this task, they have typically been evaluated in simplified scenarios and for single particles. This is particularly true for the challenging task of highly granular calorimeter simulation. For the first time, this work studies the use of highly granular generative calorimeter surrogates in a realistic simulation application. We introduce DDML, a generic library which enables the combination of generative calorimeter surrogates with realistic detectors implemented using the DD4hep toolkit. We compare two different generative models - one operating on a regular grid representation, and the other using a less common point cloud approach. In order to disentangle methodological details from model performance, we provide comparisons to idealized simulators which directly sample representations of different resolutions from the full simulation ground-truth. We then systematically evaluate model performance on post-reconstruction benchmarks for electromagnetic shower simulation. Beginning with a typical single particle study, we introduce a first multi-particle benchmark based on di-photon separations, before studying a first full-physics benchmark based on hadronic decays of the tau lepton. Our results indicate that models operating on a point cloud can achieve a favorable balance between speed and accuracy for highly granular calorimeter simulation compared to those which operate on a regular grid representation.

Neutrino telescopes are large-scale detectors designed to observe Cherenkov radiation produced from neutrino interactions in water or ice. They exist to identify extraterrestrial neutrino sources and to probe fundamental questions pertaining to the elusive neutrino itself. A central challenge common across neutrino telescopes is to solve a series of inverse problems known as event reconstruction, which seeks to resolve properties of the incident neutrino, based on the detected Cherenkov light. In recent times, significant efforts have been made in adapting advances from deep learning research to event reconstruction, as such techniques provide several benefits over traditional methods. While a large degree of similarity in reconstruction needs and low-level data exists, cross-experimental collaboration has been hindered by a lack of diverse open-source datasets for comparing methods. We present NuBench, an open benchmark for deep learning-based event reconstruction in neutrino telescopes. NuBench comprises seven large-scale simulated datasets containing nearly 130 million charged- and neutral-current muon-neutrino interactions spanning 10 GeV to 100 TeV, generated across six detector geometries inspired by existing and proposed experiments. These datasets provide pulse- and event-level information suitable for developing and comparing machine-learning reconstruction methods in both water and ice environments. Using NuBench, we evaluate four reconstruction algorithms - ParticleNeT and DynEdge, both actively used within the KM3NeT and IceCube collaborations, respectively, along with GRIT and DeepIce - on up to five core tasks: energy and direction reconstruction, topology classification, interaction vertex prediction, and inelasticity estimation.

This leads to the proposal of a novel self-supervised solution based on a masked loss function. We evaluate our method using both simulated and real data. On simulated data from a conventional video, we achieve 34.35 mean PSNR with extremely photon-sparse binary input (<0.06 photons per pixel per frame).

One of the most complex quantum networks built to date would allow 18 people to communicate securely thanks to the power of quantum physics. The researchers behind the work say it offers a practical path to building a global quantum internet, but others are sceptical. The long-promised quantum internet would allow quantum computers to communicate at distance by exchanging particles of light called photons that have been linked together by quantum entanglement . It would also allow networks of quantum sensors to be linked, or classical computers to send and receive unhackable communications. But wiring together a quantum world isn't as simple as laying down cables, because ensuring that one node of the network can be entangled with another is a challenge.

This leads to the proposal of a novel self-supervised solution based on a masked loss function. We evaluate our method using both simulated and real data. On simulated data from a conventional video, we achieve 34.35 mean PSNR with extremely photon-sparse binary input (<0.06 photons per pixel per frame).

We investigate a WIMP dark matter (DM) candidate in the form of a singlino-dominated lightest supersymmetric particle (LSP) within the $Z_3$-symmetric Next-to-Minimal Supersymmetric Standard Model. This framework gives rise to regions of parameter space where DM is obtained via co-annihilation with nearby higgsino-like electroweakinos and DM direct detection~signals are suppressed, the so-called ``blind spots". On the other hand, collider signatures remain promising due to enhanced radiative decay modes of higgsinos into the singlino-dominated LSP and a photon, rather than into leptons or hadrons. This motivates searches for radiatively decaying neutralinos, however, these signals face substantial background challenges, as the decay products are typically soft due to the small mass-splits ($Δm$) between the LSP and the higgsino-like coannihilation partners. We apply a data-driven Machine Learning (ML) analysis that improves sensitivity to these subtle signals, offering a powerful complement to traditional search strategies to discover a new physics scenario. Using an LHC integrated luminosity of $100~\mathrm{fb}^{-1}$ at $14~\mathrm{TeV}$, the method achieves a $5σ$ discovery reach for higgsino masses up to $225~\mathrm{GeV}$ with $Δm\!\lesssim\!12~\mathrm{GeV}$, and a $2σ$ exclusion up to $285~\mathrm{GeV}$ with $Δm\!\lesssim\!20~\mathrm{GeV}$. These results highlight the power of collider searches to probe DM candidates that remain hidden from current direct detection experiments, and provide a motivation for a search by the LHC collaborations using ML methods.

Quantum optical neurons (QONs) are emerging as promising computational units that leverage photonic interference to perform neural operations in an energy-efficient and physically grounded manner. Building on recent theoretical proposals, we introduce a family of QON architectures based on Hong-Ou-Mandel (HOM) and Mach-Zehnder (MZ) interferometers, incorporating different photon modulation strategies -- phase, amplitude, and intensity. These physical setups yield distinct pre-activation functions, which we implement as fully differentiable modules in software. We evaluate these QONs both in isolation and as building blocks of multilayer networks, training them on binary and multiclass image classification tasks using the MNIST and FashionMNIST datasets. Our experiments show that two configurations -- HOM-based amplitude modulation and MZ-based phase-shifted modulation -- achieve performance comparable to that of classical neurons in several settings, and in some cases exhibit faster or more stable convergence. In contrast, intensity-based encodings display greater sensitivity to distributional shifts and training instabilities. These results highlight the potential of QONs as efficient and scalable components for future quantum-inspired neural architectures and hybrid photonic-electronic systems.

Many successful families of generative models leverage a low-dimensional latent distribution that is mapped to a data distribution. Though simple latent distributions are commonly used, it has been shown that more sophisticated distributions can improve performance. For instance, recent work has explored using the distributions produced by quantum processors and found empirical improvements. However, when latent space distributions produced by quantum processors can be expected to improve performance, and whether these improvements are reproducible, are open questions that we investigate in this work. We prove that, under certain conditions, these "quantum latent distributions" enable generative models to produce data distributions that classical latent distributions cannot efficiently produce. We also provide actionable intuitions to identify when such quantum advantages may arise in real-world settings. We perform benchmarking experiments on both a synthetic quantum dataset and the QM9 molecular dataset, using both simulated and real photonic quantum processors. Our results demonstrate that quantum latent distributions can lead to improved generative performance in GANs compared to a range of classical baselines. We also explore diffusion and flow matching models, identifying architectures compatible with quantum latent distributions. This work confirms that near-term quantum processors can expand the capabilities of deep generative models.