Quantum control papers on arXiv, selected and classified automatically by QOC. https://llorebaga.github.io/QOC/topics/machine-learning-control/ 2026-10-15T00:00:00Z QOC https://arxiv.org/abs/2610.21987 2026-10-15T00:00:00Z 2026-10-15T00:00:00Z Dennis HerbMirko RossiniSabine WölkJoachim AnkerholdDominik MaileAlessio Belenchia

The use of reinforcement learning (RL) in the design of quantum control strategies for pulse level control of NISQ era quantum devices is attracting growing interest. Model-free RL, not requiring preexisting knowledge of the physical system, acts as a black-box optimization tool well suited for noisy devices. In this work, we provide a simulation-based analysis of the performance of model-free RL for state preparation and qubit gate design in a challenging setup: indirect control of NV nuclear spins in a spin-bath. In particular, the spin-bath is modeled via the generalized cluster correlation expansion accounting for magnetic impurities and intra-bath interactions. We analyze the performance of the RL agents by performing simulations with minimally observable environments and noisy, sparse rewards as introduced in (Phys. Rev. X 12, 011059), and compare them to other state-of-the-art black-box optimization tools.

https://arxiv.org/abs/2610.18776 2026-10-13T00:00:00Z 2026-10-13T00:00:00Z Finn MüßigbrodtAndraž OmahenQ. Rumman RahmanGiulio CorazzaYiwen ChuMatteo Fadel

Massive mechanical oscillators couple directly to forces, accelerations and gravity, making them attractive probes of new physics and of quantum mechanics at macroscopic scales. Pushing sensitivities beyond the standard quantum limit for signals of unknown phase requires non-Gaussian quantum states, whose metrological advantage has so far been confined to lighter systems such as trapped ions. Here we operate a microgram-scale acoustic mode of a high-overtone bulk acoustic wave resonator as a phase-insensitive quantum-enhanced sensor. A transmon qubit prepares the mode in Fock states of up to seven phonons by optimal control, and resolves its phonon-number distribution after interaction with a weak resonant signal. Bayesian analysis yields a Fisher information five times the vacuum value, a 7.0 dB gain in signal-amplitude sensitivity over any classical probe state, irrespective of its energy, currently limited by state preparation infidelities. We then train a neural network on the measured sensor response to perform Bayesian estimation without any analytical model of the system, showing the same sensitivity gain with half the systematic bias. Our results establish acoustic resonators prepared in non-Gaussian states as quantum-enhanced probes for high-frequency gravitational waves, dark matter and wave-function collapse.

https://arxiv.org/abs/2610.17193 2026-10-12T00:00:00Z 2026-10-12T00:00:00Z Niko R. ReedDeclan M. DalyAndrew J. BelingJordan D. GiandreaRonald L. WalsworthJohn W. BlanchardDaniel G. Ang

The use of artificial intelligence (AI) in physics research is increasingly common, yet few guidelines exist for its effective use. Starting with a principles-based approach, we outline a set of ten requirements for collaborative AI agents in experimental physics, spanning scientific norms, effective agent use, and domain expertise. We take a human-centered approach in which agents act as collaborators that amplify rather than replace the expertise of a human researcher (user) who directs the work and is responsible for its results. We then present a framework designed to enforce these requirements, detailing methods for improving off-the-shelf behavior of large language models (LLMs) with custom scaffolding and describing general-purpose scientific workflows and skills. In particular, we highlight the power of closed-loop campaigns where agents work iteratively toward a well-defined goal. We demonstrate the potential of this mode of research through six case studies in experimental physics, covering device design, hardware control, neural network optimization, physical model identification, and data analysis. All six case studies result in useful work products that add utility to our research, including a neural network architecture and solid-state quantum defect photodynamic model that substantially outperform our published work; a microwave waveguide design that extends a published design concept to a fabrication-ready device meeting our experimental constraints; a quantum control pulse sequence candidate that improves simulated performance by more than an order of magnitude; commissioning of an NMR spectrometer to $\sim$1~Hz frequency precision on live hardware; and finally a data-fitting pipeline that achieves, to our knowledge, the first reconstruction of the Ising microstate of an artificial spin-ice array from diffraction-limited magnetic imaging.

https://arxiv.org/abs/2610.02129 2026-10-01T00:00:00Z 2026-10-01T00:00:00Z Barry M. DillonAqib JavedJim HarkinPatryk DabkowskiBenjamin Lienhard

Fast and accurate qubit-state assignment is essential for feedback, calibration, and error correction in quantum processors. In superconducting platforms, frequency-multiplexed readout makes this task intrinsically multivariate as measured traces can encode crosstalk, qubit-state relaxation events, and other transient nonidealities that are not fully captured by conventional matched filtering. Here, we introduce spiking neural network (SNN) discriminators for superconducting qubit readout. By processing the measurement window in successive time chunks, the networks exploit temporal structure and update classification scores as data arrive, rather than waiting until the end of the readout window. The spiking networks outperform matched-filter discrimination and approach the accuracy of a full-trace artificial neural network. Beyond reaching the performance of artificial neural networks, the key advantage of SNNs is that they provide a streaming, time-resolved estimate of the qubit state that evolves as the readout signal is acquired. Using quantisation-aware training and hls4ml synthesis, we further demonstrate that each FPGA inference update can be completed before the next readout chunk arrives. These results establish spiking neural networks as a promising route to low-latency, real-time qubit readout on FPGA hardware, with broader implications for time-critical quantum-control and scientific-inference applications.

https://arxiv.org/abs/2609.24475 2026-09-21T00:00:00Z 2026-09-21T00:00:00Z Andrew Rowan BarlowHans-Martin RieserMarkus Lange

Variational hybrid quantum models are a common paradigm for realising machine learning on quantum hardware. Nonetheless, they are challenging to train due to several problems intrinsic to the loss landscapes formed by variational quantum circuits. To mitigate these issues, researchers have extended the idea of subspace controllability leading to an increase in the success rate of variational models in finding the global minimum for quantum-based tasks. However, it remains unknown whether these results extend to classical-based tasks, and if any advantages are realised over a hyperparameter search. We begin to address this question by employing controllable circuits in a multi- classification task using MNIST-1D. Our results show that over a hyperparameter search, the majority of quantum models that achieve the lowest training and validation losses are subspace controllable. These results indicate that the hyperparameter search can be restricted to such models, in turn reducing computational cost and time.

https://arxiv.org/abs/2609.08727 2026-09-08T00:00:00Z 2026-09-08T00:00:00Z Sanjeev ShapkotaYayu MoSanjaya Lohani

The Control Variational Quantum Eigensolver (ctrl-VQE) directly optimizes microwave pulses to enable faster and lower-error quantum-state preparation, but its continuous control landscape re- quires efficient search strategies. We demonstrate that a reinforcement-learning agent based on a deep Q learning network can autonomously discover high-performance pulse sequences using only system parameters and a reward function. The approach is fully general for superconducting qubit platforms, requires no ansatz, and operates at nanosecond resolution compatible with hardware con- straints. As a proof of concept, we apply the method to ground-state preparation of the Hydrogen molecule on a simulated superconducting device. The agent consistently identifies optimized control sequences that achieve high fidelity and outperform random-search baselines. These results highlight adaptive learning as a promising hardware-ready framework for pulse-level quantum control.

https://arxiv.org/abs/2608.15715 2026-08-16T00:00:00Z 2026-08-16T00:00:00Z Priyanshi SinghKrishna Bhatia

Quantum feedback control requires acting on noisy continuous measurement records without direct access to the underlying quantum state. We propose Kraus-Parameterized Belief Reinforcement Learning, a pipeline in which a recurrent encoder, constrained to the Stiefel manifold, produces density-matrix estimates that are guaranteed positive-semidefinite and trace-normalized by construction, embedding quantum state geometry directly into the learning loop. A Proximal Policy Optimization (PPO) actor then maps these physically valid belief states to continuous control actions. On a simulated continuously monitored qubit, the resulting policy achieves stable feedback control, maintaining a measurement-conditioned belief fidelity of approximately 0.77-0.80 and exhibiting substantially lower return variance than a parameter-matched LSTM-history baseline across both nominal and out-of-distribution conditions. Although gains in raw target fidelity are modest, the geometric constraint guarantees a physically valid, interpretable belief representation and yields markedly more stable control under measurement inefficiency and abrupt dynamics switches. These results indicate that physics-informed neural memory is a practical inductive bias for reliable quantum feedback control.

https://arxiv.org/abs/2608.01832 2026-08-03T00:00:00Z 2026-08-03T00:00:00Z Shi-Qiang QiaoXue-Ke SongShi-Lei SuLiu YeDong Wang

We present a reinforcement learning-optimized Rydberg electrometer based on the asymmetric blockade effect and achieve high-sensitivity electric field sensing in Rydberg arrays. Microwave dressing induces asymmetric blockade to suppress interactions between target atoms, while keeping the coupling between the central control atom and target atoms field-tunable near Förster resonance. The field-regulated blockade radius affects the detectable atomic population signals, thereby enabling electric field sensing via state-selective readout. In planar atomic arrays, classical Fisher information exhibits near-quadratic scaling with atom number and approaches the Heisenberg limit. Reinforcement learning-designed composite pulses greatly enhance quantum Fisher information by up to one order of magnitude compared with single $π$ pulses. We further establish a compact six-atom spherical configuration for vector electrometry, in which field orientation is extracted from calibrated axial populations, and weak bias fields eliminate dipole-dipole-induced sign and magic-angle ambiguities. Numerical tests against Rabi frequency deviation, positional error, residual inter-target coupling and projection noise demonstrate the reliability of this scheme. This work provides an experimentally viable approach to realize high-precision three-dimensional Rydberg electric field sensing.

https://arxiv.org/abs/2607.23276 2026-07-25T00:00:00Z 2026-07-25T00:00:00Z Martín D. JiménezMurilo D. ForlevesiEmanuel F. de LimaLeonardo K. Castelano

Achieving scalable quantum computing demands high-fidelity operations capable of mitigating population leakage into non-computational states. Physics-Informed Neural Networks (PINNs) have recently emerged as a powerful paradigm to unify quantum hardware characterization (inverse problems) and pulse engineering (direct problems), laying the foundational architecture for autonomous quantum processors. However, standard PINN frameworks face severe numerical bottlenecks, such as spectral bias, when attempting to simultaneously solve highly oscillatory multi-level dynamics and optimize continuous control fields under strict global phase constraints. In this work, we propose an enhanced PINN scheme for quantum optimal control (PINNQOC) that circumvents these limitations by incorporating Fourier feature embeddings, dynamic epoch normalization, and an informed pre-training routine. To rigorously evaluate its performance, we systematically benchmark our framework against two premier continuous control solvers: the first-order Krotov method and the second-order Projection Operator Newton Method for Trajectory Optimization (PRONTO). These techniques are applied to implement multiple quantum gates on a truncated three-level fluxonium qubit and a four-level Nitrogen-Vacancy center coupled to a Carbon-13 nuclear spin. Our advanced PINNQOC approach successfully suppresses population leakage while achieving gate fidelities exceeding 99.9$\%$, matching the efficacy of traditional solvers. Finally, we provide a comprehensive analysis of computational times, iteration efficiency, and mean leakage, highlighting the distinct trade-offs and avenues for embedding physics-guided machine learning into automated quantum hardware pipelines.

https://arxiv.org/abs/2607.20943 2026-07-23T00:00:00Z 2026-07-23T00:00:00Z Mousumi KunduAshish Kumar PatraAnurag K. S. V.Ruchika BhatSai Shankar P.Alok ShuklaJaiganesh G

Quantum Phase Estimation (QPE) is a foundational algorithm for molecular ground-state energy estimation, but its deep circuit requirements make direct hardware execution impractical on Noisy Intermediate-Scale Quantum (NISQ) devices. We present an analytically grounded variational surrogate framework in which a shallow Variational Quantum Circuit (VQC) is trained to reproduce the QPE measurement distribution without any quantum circuit simulation. The training target is computed entirely classically via the Dirichlet kernel, evaluated directly from the Full Configuration Interaction (FCI) ground-state energy, the ancilla qubit count, and the time evolution parameter, eliminating the exponentially scaling simulation bottleneck of prior surrogate approaches. We apply this framework to the hydrogen molecule (H$_2$) with a symmetry-tapered Hamiltonian, conducting a four-stage experimental investigation on IBM Quantum hardware. Stage 1 compares linear and full entangler topologies for the $R_Y$-$R_Z$-$CZ$ ansatz, with and without XpXm Dynamical Decoupling (DD), across four distributional metrics (Hellinger distance, fidelity error, total variation distance, Jensen-Shannon divergence), identifying the linear entangler as optimal. Stage 2 varies VQC layers ($p=1$ to $5$) for the linear-entangler ansatz, identifying single-layer depth as optimal under hardware noise. Stage 3 applies this configuration to the reduced $R_Y$-$CZ$ ansatz, comparing ideal and noisy simulator-trained parameters. A supplementary noise analysis at $p \in \{8,64\}$ characterizes the depth-dependent interplay between circuit depth and DD effectiveness. The framework enables faithful QPE mimicry using a linearly scaling VQC, recovering the ground-state energy within the chemical accuracy threshold (1 kcal/mol), constituting a scalable, hardware-efficient paradigm for QPE-based molecular energy estimation on NISQ devices.

https://arxiv.org/abs/2607.17498 2026-07-20T00:00:00Z 2026-07-20T00:00:00Z Yu-Qin ChenShi-Xin Zhang

Quantum optimal control (QOC) underpins adiabatic quantum computation, quantum annealing, and quantum state engineering, yet practical deployment is fundamentally bottlenecked by strict hardware constraints and substantial expert effort required to design protocols for each problem instance. To overcome this, we introduce QOC-Workbench, an auditable, large language model (LLM)-driven workflow that acts as an automated quantum co-scientist for cross-paradigm protocol design. Going beyond traditional numerical optimizers that merely tune parameters within a fixed formula, the LLM autonomously parses physics literature, proposes structural hypotheses, and writes code to validate them by direct simulation. This workflow supports cross-paradigm design by accumulating control motifs across tasks. We demonstrate this approach across three distinct settings: Case 1, Rydberg-atom maximum-independent-set arrays; Case 2, interacting XXZ spin chains; and Case 3, random transverse-field Ising models. In Cases 1 and 2, the workflow autonomously discovers hardware-compliant auxiliary controls, target catalysts, and schedule deformations that outperform literature baselines. In Case 3, it addresses the computational bottleneck of variational counterdiabatic driving by escalating from per-instance optimization to an amortized graph-neural-network generator, successfully transferring learned coefficient paths to larger unseen systems. By actively bridging the gap between theoretical algorithms and experimental restrictions across distinct control paradigms and Hamiltonian families, QOC-Workbench establishes a continuously evolving, cross-paradigm methodology for autonomous quantum control.

https://arxiv.org/abs/2607.15040 2026-07-16T00:00:00Z 2026-07-16T00:00:00Z Lorenzo VitaleShreyasi MukherjeeDario FasoneEnrico MartelloElisabetta PaladinoLuigi GiannelliGiuseppe Falci

We propose a machine-learning-empowered approach to the quantum sensing of the plaquette phase, a gauge-invariant quantity arising in three-level $Δ$ systems. This phase profoundly affects the system dynamics, breaking coherent population trapping and inducing a non-trivial phase dependence of the dynamics. We demonstrate that a multi-layer perceptron (MLP), trained in a supervised-learning framework, can accurately estimate the plaquette phase from STImulated Raman Adiabatic Passage (STIRAP) population transfer efficiencies measured under different driving conditions, which provide experimentally accessible observables. Our results highlight how the combination of coherent control and machine learning (ML) enables effective phase identification in closed-loop quantum systems, opening new perspectives for quantum technologies, specifically quantum sensing applications including synthetic gauge fields.

https://arxiv.org/abs/2607.14884 2026-07-16T00:00:00Z 2026-07-16T00:00:00Z Yao DuJian-Jian ChengLin ZhangMing-Liang HuXingang Wang

Quantum gate design is often represented as pulse optimization, although the physical object that implements a gate is the full controlled evolution generated by the pulse. Here we use physics-informed neural networks to represent single-qubit gate design at this evolution level: the control fields, the Bloch-state trajectories, and the total duration are learned together under the Bloch equation. This changes the optimized object from pulse amplitudes to a differentiable physical process whose structure can be inspected and refined. For rotation gates, the optimized evolutions recover the physical organization expected for bounded single-qubit control, with no prescribed pulse ansatz or duration scan. For a geometric gate, the representation identifies localized bottlenecks in maintaining the geometric condition and turns this diagnosis into feedback, reducing the residual path error while preserving high fidelity. Thus physics-informed learning is used not only to synthesize gates, but also to make optimized quantum controls physically readable, diagnosable, and locally refinable. This process-level view may be especially useful for adapting gates to hardware-specific, task-specific, and locally varying experimental constraints.

https://arxiv.org/abs/2607.13887 2026-07-15T00:00:00Z 2026-07-15T00:00:00Z Francesco CaravelliRoberto MentaAntonio Sannia

Quantum gate synthesis is essential for implementing quantum algorithms on real hardware, yet existing methods are often computationally demanding. Here, we introduce a novel approach based on reservoir computing, which we name Group Reservoir Computing, an efficient machine-learning paradigm for learning temporal dynamics whose training reduces to a single linear regression, to reduce the resources required. The method is grounded in the Wei--Norman decomposition, which provides a compact description of the evolution. We prove that the reconstructed dynamics always remain unitary by construction and derive formal error bounds that establish the theoretical validity of the strategy. On the standard single-qubit gate set the trained network produces a control pulse in a single pass, with mean fidelity 0.94 across the eight benchmark gates; used to warm-start gradient-based optimization, it roughly halves the number of iterations that plain gradient ascent needs to reach a target fidelity, so that the relevant figure of merit is the time to reach that threshold rather than the final accuracy after a fixed budget. Owing to its general formulation, the method applies to any finite-dimensional hardware platform; the route to multiqubit synthesis is discussed in the closing section.

https://arxiv.org/abs/2607.12567 2026-07-14T00:00:00Z 2026-07-14T00:00:00Z Zhao-Wei WangKai-Yu YuanFeng-Hua RenZhao-Ming Wang

Physics-informed neural networks (PINNs) provide a pathway to reunify the simulation and control of quantum systems, in which these two tasks are typically decoupled in traditional strategies. However, most work remains confined to Markovian environments. When applied to non-Markovian systems, standard PINN architectures fail to converge reliably due to multi-objective optimization conflicts arising from the coupled differential equations. To address this fundamental limitation, we extend our previously proposed forked PINN (FPINN) by incorporating a dedicated control branch. By decoupling the optimization objectives at the gradient level via selective gradient flow, our method turns a previously intractable multi-task optimization into a well-conditioned one, allowing simulation and control to be optimized jointly without compromise. Numerical simulations on a two-qubit Heisenberg XXX model confirm that our framework faithfully reproduces the features of non-Markovian dynamics, including decoherence and information backflow. Taking a state-preparation task on the same model as an example, our FPINN achieves higher fidelity than gradient ascent pulse engineering, chopped random basis, and standard PINNs, with the advantage becoming more pronounced as the environment becomes more dissipative and more Markovian. The generated pulses are also noticeably smoother, which is advantageous for experimental implementation. Our framework thus provides a unified, end-to-end differentiable paradigm for simulation and control of open quantum systems, with potential implications for quantum computing, simulation, and control.

https://arxiv.org/abs/2606.31534 2026-06-30T00:00:00Z 2026-06-30T00:00:00Z Svitlana MatsenkoAmirhossein GhazisaeidiMarcin JarzynaMateusz KucharczykMikkel N. SchmidtKonrad BanaszekDarko Zibar

Practical hardware limitations, including finite transmitter and receiver filter lengths as well as the finite resolution of digital-to-analog and analog-to-digital converters, lead to mode mismatch and degrade the performance of continuous-variable quantum key distribution systems. To address this, we develop a machine learning-based end-to-end optimization framework that jointly optimizes transmitter pulse shaping and receiver matched filtering. The approach employs reinforcement learning under realistic hardware constraints, including a limited number of filter taps, finite digital-to-analog and analog-to-digital converter resolution, analog low-pass filtering, and the optimal mean photon number. By mitigating mode mismatch and accounting for implementation constraints, the proposed method improves overall system performance. Simulation results demonstrate enhanced secure key rates compared to conventional approaches, demonstrating the effectiveness of the proposed framework.

https://arxiv.org/abs/2606.30765 2026-06-29T00:00:00Z 2026-06-29T00:00:00Z Matthew L. PetersGuoqing WangDavid C. SpieringsNiv DruckerMeng-Wei ChenAudrey BartlettIsaac L. ChuangVladan Vuletić

Real-time feedback control of quantum systems is often limited by partial observations, nonlinear dynamics and measurement noise, which make accurate model-based controllers difficult to design. Here we show that deep reinforcement learning can cool the motion of a single neutral atom coupled to a high-finesse optical cavity using only the continuously monitored cavity transmission. We first train the controller in simulation and then transfer it to the experiment, where online fine-tuning adapts it to unmodeled experimental dynamics. The learned policy damps the atom's motion in real time and achieves a cooling time constant of 388 +/- 14 microseconds, corresponding to only two motional periods in the trap. It also outperforms a standard linear differentiator controller in cooling speed while maintaining comparable atom retention over a broad range of operating conditions. These results establish reinforcement learning as a practical strategy for feedback control in quantum-limited experiments where compact analytical models are incomplete.

https://arxiv.org/abs/2606.29610 2026-06-28T00:00:00Z 2026-08-04T00:00:00Z Murilo D. ForlevesiEmanuel F. de LimaEdson Denis Leonel

We present a Physics-Informed Neural Quantum Control (PINQC) framework for rovibrational photoassociation in a Morse molecular system. The proposed method combines neural-network-based laser-field generation with differentiable quantum propagation, allowing optimized laser pulses to be obtained directly from the underlying quantum dynamics without requiring external training data. The optimized control fields efficiently transfer an initially continuum-like Gaussian wave packet into the vibrational ground-state level, promoting continuum-to-bound population transfer through coherent rovibrational dynamics. The resulting photoassociation process involves both vibrational stabilization and rotational redistribution arising naturally from dipole-induced couplings between neighboring rotational channels. A central result of the present work is the successful application of the PINQC framework to extended rovibrational models containing larger rotational levels than those previously accessible in our conventional photoassociation calculations. The optimization remains numerically stable despite the increased complexity of the molecular system, demonstrating that differentiable optimization provides an effective strategy for treating rovibrational models of increased dimensionality. These results establish the PINQC framework as a promising computational tool for molecular photoassociation and motivate future investigations of increasingly complex rovibrational quantum-control problems.

https://arxiv.org/abs/2606.25795 2026-06-24T00:00:00Z 2026-06-24T00:00:00Z Yu-Han ChangIlya MoskalenkoMarko KuzmanovićOgnjen StanisavljevićIsak BjörkmanDavid Díez-IbáñezYikun GuAkash V. DixitIgor G. IrastorzaGheorghe Sorin Paraoanu

We report on an improved microwave detection protocol for dark matter candidates such as the axion and the dark photon. We employ a superconducting transmon qubit dispersively coupled to a double-cavity system, enabling quantum non-demolition measurements of the photon occupation in a relatively short-lived storage cavity. To reduce the experimental cycle time and enhance sensitivity for axion and dark-photon searches, we operate this detector in a regime of increased qubit-cavity coupling, resulting in Stark shifts of 4.6 MHz. In this regime, conventional control pulses suffer from strong frequency-detuning sensitivity and photon-number-dependent errors. We address this limitation by implementing frequency-detuning-robust $π/2$ pulses (obtained by machine-learning optimization) that preserve high-fidelity qubit control over a bandwidth of approximately 20 MHz. We experimentally validate this protocol and demonstrate single-photon detection performance comparable to previous implementations, despite significantly reduced qubit coherence times and storage-cavity lifetimes. Using parity-based measurement sequences combined with a Hidden Markov Model (HMM) analysis, we achieve background rates on the order of $\mathcal{O}(20)$ Hz. In the absence of a magnetic field, we derive exclusion limits on the dark photon model for dark matter, reaching a sensitivity to the kinetic mixing angle of $ε_{95\%} \sim 1\times10^{-14}$ at 5.051 GHz. These results establish machine-learning robust control as a key enabler for faster, more scalable microwave quantum sensors for dark-matter searches.

https://arxiv.org/abs/2606.24507 2026-06-23T00:00:00Z 2026-06-23T00:00:00Z Tobias KiermeyerThomas HeydenreichLéo Van DammeSebastian HohenemserFlorian MarquardtSteffen J. Glaser

Real-time adaptive control of quantum systems requires rapid generation of robust, high-fidelity pulses across a continuous range of operating conditions. Standard optimization algorithms such as gradient-ascent pulse engineering (GRAPE) solve each instance independently, discarding information between runs and requiring costly reinitialization when parameters change. We present an approach to robust optimal quantum control based on model-based reinforcement learning, in which a single neural network -- embedding the Hamiltonian directly into the training pipeline -- generates robust gates across an entire family of gate configurations, without pre-computed training data. Demonstrated on a single-spin (two-level) system, the trained networks produce pulses for arbitrary rotation angles over a range of pulse durations, detunings, and field inhomogeneities in milliseconds, at fidelities comparable to multi-seed GRAPE. The framework is inherently adaptable: any parameter entering the Hamiltonian can serve as a network input, extending the approach to different systems and control settings. Beyond speed, the network reveals structure in the control landscape: it discovers the same structured phase profiles that appear in GRAPE solutions -- made identifiable through fidelity-invariant symmetry transformations -- but more consistently than independent optimization. This consistency enables smooth interpolation across the entire trained parameter space.

https://arxiv.org/abs/2606.21758 2026-06-19T00:00:00Z 2026-06-19T00:00:00Z Yiping LuYulong HuZhuzheng HanShirong Lin

Quantum systems face inherent challenges in achieving precise control, and solving the Schrödinger equation is often intractable for complex hybrid platforms. Here, for the first time, we introduce a magnon into a feedback-controlled quantum system. To solve the dynamics numerically and efficiently, we employ a Long Short-Term Memory network, a machine learning approach, to propagate the probability amplitudes to the steady state. By applying coherent feedback, we effectively stabilize the intracavity state. Our results reveal that the photon-photon correlation function and the concurrence, a measure of magnon-atom entanglement, exhibit periodic oscillations with the cavity-mirror distance, and that feedback significantly enhances both antibunching and bunching when the detuning is varied. These findings not only demonstrate the power of artificial intelligence in quantum dynamics simulation, but also open a promising route for on-demand quantum state engineering in hybrid magnonic systems, with potential applications in quantum networks and quantum information processing.

https://arxiv.org/abs/2606.19947 2026-06-18T00:00:00Z 2026-06-18T00:00:00Z Merijn MoodyZier MenschMiranda C. N. ChengPeter G. BolhuisMax Welling

Reliable quantum control in the presence of decoherence requires policies that combat the effect of environmental noise on the controlled dynamics. Open quantum systems under continuous monitoring generate classical measurement records whose drift depends on the noise experienced by the system; the records of two evolutions sharing the same decoherence channels differ only in this drift, so Girsanov's theorem yields a closed-form, differentiable estimator of the KL divergence between their trajectory distributions. We instantiate this estimator with two physically motivated reference measures, yielding two regularizers that both drive the system toward states where the effects of decoherence are minimal: the Wiener KL (KL_W), which is empirically more effective under certain conditions on the noise model, and the drift-variance regularizer (R_DV), which works for all noise models. Both are qualitatively distinct from existing penalties on control fluence or smoothness: they penalize the observable consequences of control on the decoherence channels rather than the control amplitude itself. The regularizers outperform unregularized gradient-based and reinforcement-learning baselines across a range of open quantum systems -- including single- and multi-qubit benchmarks and a multi-qubit chain calibrated to a published snapshot of the IBM Kingston processor -- along several axes of evaluation: final-state fidelity, robustness to mismatch in the assumed noise model (gains grow from +17 pp at training noise to +27 pp under 2.5x noise mismatch), and occupation of forbidden states. The regularizers reduce infidelity by up to 50%, with ~16% gains on the calibrated IBM Kingston chain.

https://arxiv.org/abs/2606.15769 2026-06-14T00:00:00Z 2026-06-14T00:00:00Z Ali Abu-NadaSubhashish BanerjeeLian-Ao Wu

Protecting quantum coherence against realistic environmental noise remains one of the fundamental obstacles to scalable quantum technologies. We develop a noise-adaptive dynamical decoupling framework that combines analytical open-quantum-system modeling with machine-learning-based forecasting for a qubit interacting with random telegraph noise. Unlike conventional dynamical decoupling protocols based on fixed pulse schedules, the proposed approach continuously forecasts short-time coherence evolution and adaptively applies control pulses according to the instantaneous noise dynamics. We investigate stationary and non-stationary environments spanning both Markovian and non-Markovian regimes. Numerical simulations demonstrate that the machine-learning-assisted adaptive control strategy substantially outperforms conventional periodic dynamical decoupling while using a comparable number of control pulses. The improvement becomes particularly pronounced in non-Markovian and non-stationary regimes, where memory effects, coherence revivals, and temporally evolving noise strongly limit the effectiveness of static pulse protocols. These results establish predictive machine-learning-assisted dynamical decoupling as a promising and scalable framework for adaptive quantum control in realistic noisy quantum devices.

https://arxiv.org/abs/2606.13005 2026-06-11T00:00:00Z 2026-06-11T00:00:00Z Xiaotian NieTao ZhangLinghui Chen

Ground-state preparation is a critical task in quantum simulation and quantum computing, as it enables the study of correlated phases and the generation of entangled resource states. While measurement--feedback control has emerged as a promising route to state preparation, existing schemes either rely on handcrafted, task-specific policies or are designed using full quantum-state information that is unavailable in real experiments and becomes impractical for large many-body systems. Here we develop an adaptive measurement--feedback protocol based on reinforcement learning under partial observability. The controller uses only the history of experimentally accessible measurement outcomes to choose both the measurement operator and the feedback action in real time. To make training compatible with experiments, we introduce a stochastic terminal reward built from one-shot measurements of randomly sampled Hamiltonian components, avoiding unphysical full-state reconstruction while remaining an unbiased estimator of the target energy. We demonstrate the method by preparing ground states of the Bose--Hubbard model and by generating GHZ states, establishing a scalable and hardware-compatible route to quantum state preparation.

https://arxiv.org/abs/2606.02014 2026-06-01T00:00:00Z 2026-06-01T00:00:00Z Piero LuchiFrancesco Pederiva

We present a framework combining Lie group theory and feed-forward neural networks to efficiently generate quantum optimal control pulses for arbitrary unitary operations in superconducting qubit systems, bypassing the need for explicit optimization at inference time. The exponential scaling of the Hilbert space dimension with qubit number makes standard optimization approaches computationally prohibitive when large ensembles of distinct propagators must be processed, a bottleneck that is particularly acute in Trotterized quantum simulation. Our method addresses this limitation by pre-computing a representative set of control pulses via Lie group theory and training neural networks to map target propagators to their corresponding pulses. We demonstrate the approach on superconducting qubit systems of 2, 3, and 4 qubits, finding high reconstruction fidelity for specific combinations of Lie algebra parameters. As a physically motivated benchmark, we apply the methodology to reconstruct control pulses for the Trotter propagators of a neutrino system undergoing collective flavor oscillations. The successful generalization across system types demonstrates that a single model -- trained once on hardware-specific random propagators -- can serve as a universal control-pulse generator for any target quantum system of compatible Hilbert space dimension, offering a promising route toward scalable quantum simulation.

https://arxiv.org/abs/2606.00353 2026-05-29T00:00:00Z 2026-07-19T00:00:00Z Ebrahim KhaleghianÖzgür E. Müstecaplıoğlu

We study whether limited finite-shot calibration measurements from a hidden transmon-inspired simulator can be used to learn compact, task-relevant effective error models for variational-algorithm reliability. Each physical element is modeled as a weakly anharmonic qutrit with coherent control imperfections, dissipation, dephasing, leakage, readout assignment error, and sampling noise, while the learner receives only selected local tomography data and, in the three-qubit extension, targeted pair probes. The learned objects are local affine Bloch response maps supplemented by process-relative edge residuals, and they are tested through their ability to reproduce and mitigate deformations of QAOA/MaxCut cost landscapes in simulation. The results show that strongly incomplete local data can still support useful response-map inference, that regularized linear models become competitive with neural networks in the scaled three-qubit setting, and that pair probes provide useful edge-level information, giving the clearest edge-residual prediction gain at the full pair-probe budget and a measurable downstream QAOA benefit. In the best non-oracle test, a Clifford-data-regression-style local-inverse correction reduces the finite-shot QAOA landscape error from $0.18187\,[0.17576,0.18798]$ to $0.01811\,[0.01751,0.01871]$, corresponding to a $10\times$ improvement. The study supports a hardware-aware, measurement-efficient calibration strategy, while incorporating leakage-explicit diagnostics and a non-oracle regression-style correction.

https://arxiv.org/abs/2605.26925 2026-05-26T00:00:00Z 2026-05-26T00:00:00Z Haftu W. FentawSteve CampbellSimon Caton

We present a Multi-task Soft Actor-Critic (SAC) Reinforcement Learning framework designed for open-system quantum control across diverse Hamiltonians, which learns optimal pulse sequences while simultaneously discovering problem-specific evolution time T and number of control pulse segments N. Experimental results across 51 Hamiltonian variations demonstrate that the multi-task SAC model is able to generate control pulses that can drive a system, under environment noise, from its initial state to its target state with high fidelities, establishing essential foundations for universal quantum control applicable to realistic noisy quantum devices. Through progressive expansion of the training Hamiltonian set, we investigate if a single multi-task model trained using a given number of sample Hamiltonians can successfully accomplish state-transfer tasks for Hamiltonians drawn from the same Hamiltonian space but not encountered during training. In addition, our Robustness Infidelity Measure (RIM) analysis reveals that SAC trained policies exhibit superior robustness to pulse amplitude perturbations and decoherence rate variations compared to GRAPE-optimized controls.

https://arxiv.org/abs/2605.26021 2026-05-25T00:00:00Z 2026-05-25T00:00:00Z Yusheng ZhaoHan WangXin LiuXinjie SongJixi HeLingwei SongYuanhe JiKen DengRunqing ZhangZhiguo HuangLing QianJize HanDi Luo

Quantum control is essential for quantum information science and technology, yet designing high-fidelity control protocols remains challenging due to complex optimization landscapes, hardware noise, and long pulse sequences. Existing numerical solvers often require problem-specific engineering and produce opaque control amplitudes, while naive large language models (LLMs) lack the physical consistency and long-horizon precision for reliable quantum control synthesis. Here we introduce VF-QCTRL, a physics-informed large language model framework for general quantum control that combines symbolic reasoning with optimization to propose analytic control ansätze and coherently refine their parameters through feedback. To systematically evaluate LLM-driven quantum control, we develop QCTRL-BENCH, a benchmark spanning sixteen tasks across single- and multi-qubit systems, closed and open quantum dynamics, noiseless and noisy settings, and both analytic and numerical protocols. Across the benchmark, VF-QCTRL demonstrates strong universality, accuracy, efficiency, and interpretability: it applies to generic quantum control systems without task-specific training, achieves performance competitive with or exceeding state-of-the-art conventional solvers in both noiseless and noisy regimes with query efficiency, exhibits favorable inference-time scaling and pulse resolution scaling, and derives physically interpretable analytical protocols directly from prompts. Our results establish physics-informed LLM-based quantum control as a promising paradigm for accurate, efficient, interpretable, and training-free quantum control protocol design across a broad range of quantum systems.

https://arxiv.org/abs/2605.25066 2026-05-24T00:00:00Z 2026-05-24T00:00:00Z Esra Yeniaras

Quantum machine learning (QML) is moving from research prototypes to deployed cloud services. As QML enters regulated industries, the integrity of the quantum stage becomes a practical concern on two fronts: noisy hardware drifts at the channel level between recalibrations, and an adversary with control over the execution environment can substitute the declared quantum channel with a behaviorally similar but mathematically distinct one. Neither concern is covered by existing QML verification work on pulse-level noise, input drift, input-perturbation robustness, or device identity. We introduce QML-PipeGuard, a contract-based framework addressing both concerns under a single mathematical machinery. It characterizes a QML pipeline at runtime by its behavioral fingerprint, the vector of observable expectation values under a tomographically structured measurement family, and operates in two modes: drift-aware monitoring that absorbs benign calibration changes within a calibrated tolerance, and adversarial detection that catches channel substitution as a violation of an informationally complete observable contract. The framework contributes a pipeline-composition treatment of the encoder-ansatz-measurement channel with a QML-specific threat model (tight frame-bound C=sqrt(3) for the single-qubit Pauli family), a finite-shot sample-complexity bound, and a tolerance decomposition separating adversarial and natural-drift contributions. We validate the framework end-to-end on a two-qubit QSVM pipeline on the IBM Heron r2 processor (ibm_fez), with a sample-complexity validation on a noise-matched simulator. The prescribed measurement budget (about 1.4e4 shots) fits in a single batched job, the sneaky channel is detected with a wide safety margin while evading the weak contract, and the typical hardware drift sits within tolerance.

https://arxiv.org/abs/2606.20606 2026-05-21T00:00:00Z 2026-05-21T00:00:00Z Atit PokharelShaba ShaonThomas MorrisDinh C. Nguyen

Distributed quantum learning (DQL) has emerged as a promising paradigm to scale quantum-enhanced machine learning by interconnecting multiple quantum devices. However, for efficient real-world deployment, it is essential to characterize how DQL converges under practical scenarios while simultaneously safeguarding multi-device quantum infrastructures from evolving security threats. Addressing these aspects in an integrated manner is key to ensuring both performance and resilience in large-scale DQL systems. Therefore, this paper presents a new DQL study where our innovation lies in: (i) conducting a holistic convergence analysis for DQL under practical settings, i.e., partial device participation, non-convex loss functions, and heterogeneous data distributions, (ii) developing a novel multi-layered post-quantum cryptographic architecture with a quantum neural network-powered adaptive mechanism that monitors conditions, evaluates threats, and adjusts parameters across three National Institute of Standards and Technology (NIST)-compliant levels. Our theoretical framework and empirical validation reveal two key insights: (i) the derived convergence bound uncovers a fundamental trade-off between convergence rate, measurement shots, and the size of the participating device subset; and (ii) findings from our evaluations on a physical testbed modeling quantum control architectures expose the performance limitations of static post-quantum security, while confirming that our adaptive framework effectively mitigates these overheads to preserve overall system efficiency. Specifically, the hardware experiments demonstrate that our dynamic security mechanism reduces total security execution time by approximately 49% relative to static high-security baselines, while maintaining a threat detection accuracy of over 91%. Furthermore, extensive simulations validate our theoretical analysis.....