Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

ACM/IEEE Design Automation Conference (DAC)

Time-Aware Active Calibration and Scheduling for N-Qubit Systems via Bayesian Optimization and Reinforcement Learning

Z. Zhao, Tingting Li, Xiaofei Yue, Zhaoxuan Li, Jianwei Yin

Published Jul 26, 2026• 0 citations
Publisher

Abstract

Frequent recalibration of multi-qubit systems is essential to maintain hardware fidelity, but calibration itself is costly and subject to rapid parameter drift. This work presents a novel framework for time-aware active calibration that combines Bayesian Optimization (BO) and Reinforcement Learning (RL) to adaptively schedule and prioritize calibration experiments under uncertainty. We model the calibration landscape as a directed acyclic graph (DAG), where nodes represent hardware parameters (e.g., frequency, amplitude ratio, DRAG, or phase) and edges capture inter-parameter dependencies extracted automatically from Qiskit Experiments metadata. Each parameter's temporal drift is modeled as an Ornstein-Uhlenbeck (OU) or exponential decay process with uncertainty bounds. The BO agent prioritizes the next calibration target using a time-aware acquisition score that balances expected improvement, predictive uncertainty, and experiment duration under system-level constraints. A parallel RL scheduler coordinates cross-qubit calibration and readout tasks to minimize idle time and avoid conflicts. Our system further incorporates self-triggered recalibration based on online RB/XEB health metrics, enabling autonomous recovery from drift without human intervention. Experimental evaluation on multi-qubit testbeds demonstrates improved calibration efficiency, longer mean time between recalibrations (MTBC), and reduced overall calibration overhead compared to fixed or purely heuristic scheduling baselines.

DOI
10.1145/3770743.3804388

Related papers

AI-Assisted Control Systems for Quantum Hardware Optimization

Clara Schmidt, Isabella Rossi

Quantum hardware control -- the precise calibration of microwave pulses, flux biases, and laser parameters that drive qubit operations -- is a critical bottleneck in scaling superconducting and trapped-ion quantum processors. Manual calibration is time-consuming, requires expert domain knowledge, and fails to adapt to rapid parameter drift between calibration cycles. AI-assisted control systems offer automated, adaptive alternatives using reinforcement learning (RL), Bayesian optimisation (BO), and neural network surrogate models to continuously optimise hardware control parameters. This paper proposes the AI Quantum Control Framework (AQCF), evaluating six AI control strategies across five hardware optimisation tasks: single-qubit gate calibration, two-qubit gate optimisation, crosstalk suppression, readout fidelity maximisation, and real-time drift compensation. AQCF is evaluated on IBM Quantum Eagle and IonQ Aria hardware over 60-day continuous operation. Key results: RL-based pulse optimisation improves two-qubit gate fidelity by 18.4% over manual calibration; Bayesian optimisation reduces calibration time by 84% (from 4.2 hours to 40 minutes); neural surrogate models enable real-time drift compensation with 12.8-minute response latency. The framework introduces the AI Control Efficiency Score (ACES) and a deployment roadmap for autonomous quantum hardware management.

Quantum Frontiers Journal•Nov 18, 2025•0 citations

Universal Graph-Based Scheduling for Quantum Systems

Leon Riesebos, Brad Bondurant, Kenneth R. Brown

High fidelity operation of a quantum system requires precise tuning of control parameters. Calibration of a quantum system is often achieved by running complex series of dependent experiments and a full system calibration can require tens of calibration experiments to complete. Optimal control parameters drift over time, and components of experimental quantum systems are susceptible to failure. Hence, continuous operation of a quantum system requires automated background processes such as frequent recalibration and monitoring. In this article, we present a scheduling toolkit that schedules experiments based on a directed acyclic graph using a configurable traversal algorithm. Our scheduler can be triggered from any process, enabling universal feedback between the scheduler and the quantum control system. To demonstrate the capabilities of our system, we implemented a complex system calibration algorithm based on our scheduling toolkit.

IEEE Micro•Jul 7, 2021•8 citations

Model-aware reinforcement learning for high-performance Bayesian experimental design in quantum metrology

Federico Belliardo, Fabio Zoratti, Florian Marquardt +1 more

Quantum sensors offer control flexibility during estimation by allowing manipulation by the experimenter across various parameters. For each sensing platform, pinpointing the optimal controls to enhance the sensor's precision remains a challenging task. While an analytical solution might be out of reach, machine learning offers a promising avenue for many systems of interest, especially given the capabilities of contemporary hardware. We have introduced a versatile procedure capable of optimizing a wide range of problems in quantum metrology, estimation, and hypothesis testing by combining model-aware reinforcement learning (RL) with Bayesian estimation based on particle filtering. To achieve this, we had to address the challenge of incorporating the many non-differentiable steps of the estimation in the training process, such as measurements and the resampling of the particle filter. Model-aware RL is a gradient-based method, where the derivatives of the sensor's precision are obtained through automatic differentiation (AD) in the simulation of the experiment. Our approach is suitable for optimizing both non-adaptive and adaptive strategies, using neural networks or other agents. We provide an implementation of this technique in the form of a Python library called qsensoropt, alongside several pre-made applications for relevant physical platforms, namely NV centers, photonic circuits, and optical cavities. This library will be released soon on PyPI. Leveraging our method, we've achieved results for many examples that surpass the current state-of-the-art in experimental design. In addition to Bayesian estimation, leveraging model-aware RL, it is also possible to find optimal controls for the minimization of the Cramér-Rao bound, based on Fisher information.

arXiv:2312.16985•Quantum•Dec 10, 2024•11 citations

Real-Time DCZ Gate Control by Bayesian Optimization with Forgetting

Yudai Sato, T. Kawahara

Silicon spin qubits are a promising platform for large-scale quantum computing because of their compatibility with advanced semiconductor fabrication technology. However, charge noise remains a major challenge since it causes timedependent drifts in qubit frequency and exchange interactions through electric field fluctuations. These drifts in control parameters are one obstacle to achieving the high-fidelity quantum operations required for quantum error correction. In this work, we propose a Bayesian optimization (BO) framework for the adaptive calibration of quantum gate parameters in silicon qubits. In addition, to address the impact of charge noise, which exhibits a$1 / f$-like power spectral density, we incorporate a forgetting mechanism into the Gaussian process model used during optimization. Our simulations on a realistic silicon quantum dot system show that BO-based method improves gate fidelity by 0.266% and reduces calibration iterations by 36.9% compared to random search. Compared to standard BO, our modified method achieves a further fidelity gain of 0.008% and a 9.23% reduction in iterations. These results highlight the potential of BO-based calibration for robust quantum gate implementation under realistic noise conditions.

IEEE International Conference on Quantum Computing and Engineering (QCE)•Aug 30, 2025•0 citations

Optimized Bayesian system identification in quantum devices

Thomas M. Stace, Jiayin Chen, Li Li +6 more

Identifying and calibrating quantitative dynamical models for physical quantum systems is important for a variety of applications. Here we present a closed-loop Bayesian learning algorithm for estimating multiple unknown parameters in a dynamical model, using optimized experimental ``probe'' controls and measurement. The estimation algorithm is based on a Bayesian particle filter, and is designed to autonomously choose informationally optimized probe experiments with which to compare to model predictions. We demonstrate the performance of the algorithm in both simulated calibration tasks and in an experimental single-qubit ion-trap system. Experimentally, we find that, with $60$ times fewer samples, we exceed the precision of conventional calibration methods, delivering an approximately $93$ times improvement in efficiency (as quantified by the reduction of measurements and resets required to achieve a target residual uncertainty and multiplied by the increase in accuracy). In simulated and experimental demonstrations, we see that successively longer pulses are selected as the posterior uncertainty iteratively decreases, leading to an exponential improvement in the accuracy of model parameters with the number of experimental queries, and a commensurate increase in the per-query time.

arXiv:2211.09090•Physical Review Applied•Jan 9, 2024•10 citations

Automatic_Calibration_System_by_Reinforcement_Learning

Walter Ayala

This document presents a rigorous experimental framework for investigating automatic cal-ibration of superconducting qubits using reinforcement learning (RL). The calibration problemis formulated initially as a partially observable Markov decision process (POMDP), becausethe physical state of the device is not directly observable. A reduced MDP representationmay be used only when the measured state vector is demonstrably sufficient for the selectedcontrol task.The controller receives experimentally accessible observables, selects bounded calibrationactions, and receives a reward constructed from measurable calibration-quality metrics, actioncost, and safety constraints. A digital twin is used for offline training, while the final evaluationis performed on hardware under a frozen evaluation protocol.Version 3.1 introduces explicit separation between training, validation, and evaluation data;a formal sim-to-real analysis; a safety supervisor and deterministic fallback controller; latencyand drift-timescale requirements; preregistered primary and secondary endpoints; paired ex-perimental blocks; cooldown-level clustering; bootstrap and hierarchical statistical analysis;placebo and ablation tests; and reproducibility requirements.The primary endpoint is the difference in time-above-threshold between the RL controllerand a matched baseline controller. The analysis is designed to distinguish genuine adaptivecalibration from improvements caused by resource imbalance, initial-condition differences,reward leakage, hardware drift, or statistical artifacts.No experimental improvement is claimed in this document.

•Sep 24, 2026•0 citations
Frequent recalibration of multi-qubit systems is essential to maintain hardware fidelity, but calibration itself is costly and subject to rapid parameter drift. This work presents a novel framework for time-aware active calibration that combines Bayesian Optimization (BO) and Reinforcement Learning (RL) to adaptively schedule and prioritize calibration experiments under uncertainty. We model the calibration landscape as a directed acyclic graph (DAG), where nodes represent hardware parameters (e.g., frequency, amplitude ratio, DRAG, or phase) and edges capture inter-parameter dependencies extracted automatically from Qiskit Experiments metadata. Each parameter's temporal drift is modeled as an Ornstein-Uhlenbeck (OU) or exponential decay process with uncertainty bounds. The BO agent prioritizes the next calibration target using a time-aware acquisition score that balances expected improvement, predictive uncertainty, and experiment duration under system-level constraints. A parallel RL scheduler coordinates cross-qubit calibration and readout tasks to minimize idle time and avoid conflicts. Our system further incorporates self-triggered recalibration based on online RB/XEB health metrics, enabling autonomous recovery from drift without human intervention. Experimental evaluation on multi-qubit testbeds demonstrates improved calibration efficiency, longer mean time between recalibrations (MTBC), and reduced overall calibration overhead compared to fixed or purely heuristic scheduling baselines.
Quantum hardware control -- the precise calibration of microwave pulses, flux biases, and laser parameters that drive qubit operations -- is a critical bottleneck in scaling superconducting and trapped-ion quantum processors. Manual calibration is time-consuming, requires expert domain knowledge, and fails to adapt to rapid parameter drift between calibration cycles. AI-assisted control systems offer automated, adaptive alternatives using reinforcement learning (RL), Bayesian optimisation (BO), and neural network surrogate models to continuously optimise hardware control parameters. This paper proposes the AI Quantum Control Framework (AQCF), evaluating six AI control strategies across five hardware optimisation tasks: single-qubit gate calibration, two-qubit gate optimisation, crosstalk suppression, readout fidelity maximisation, and real-time drift compensation. AQCF is evaluated on IBM Quantum Eagle and IonQ Aria hardware over 60-day continuous operation. Key results: RL-based pulse optimisation improves two-qubit gate fidelity by 18.4% over manual calibration; Bayesian optimisation reduces calibration time by 84% (from 4.2 hours to 40 minutes); neural surrogate models enable real-time drift compensation with 12.8-minute response latency. The framework introduces the AI Control Efficiency Score (ACES) and a deployment roadmap for autonomous quantum hardware management.
High fidelity operation of a quantum system requires precise tuning of control parameters. Calibration of a quantum system is often achieved by running complex series of dependent experiments and a full system calibration can require tens of calibration experiments to complete. Optimal control parameters drift over time, and components of experimental quantum systems are susceptible to failure. Hence, continuous operation of a quantum system requires automated background processes such as frequent recalibration and monitoring. In this article, we present a scheduling toolkit that schedules experiments based on a directed acyclic graph using a configurable traversal algorithm. Our scheduler can be triggered from any process, enabling universal feedback between the scheduler and the quantum control system. To demonstrate the capabilities of our system, we implemented a complex system calibration algorithm based on our scheduling toolkit.
Quantum sensors offer control flexibility during estimation by allowing manipulation by the experimenter across various parameters. For each sensing platform, pinpointing the optimal controls to enhance the sensor's precision remains a challenging task. While an analytical solution might be out of reach, machine learning offers a promising avenue for many systems of interest, especially given the capabilities of contemporary hardware. We have introduced a versatile procedure capable of optimizing a wide range of problems in quantum metrology, estimation, and hypothesis testing by combining model-aware reinforcement learning (RL) with Bayesian estimation based on particle filtering. To achieve this, we had to address the challenge of incorporating the many non-differentiable steps of the estimation in the training process, such as measurements and the resampling of the particle filter. Model-aware RL is a gradient-based method, where the derivatives of the sensor's precision are obtained through automatic differentiation (AD) in the simulation of the experiment. Our approach is suitable for optimizing both non-adaptive and adaptive strategies, using neural networks or other agents. We provide an implementation of this technique in the form of a Python library called qsensoropt, alongside several pre-made applications for relevant physical platforms, namely NV centers, photonic circuits, and optical cavities. This library will be released soon on PyPI. Leveraging our method, we've achieved results for many examples that surpass the current state-of-the-art in experimental design. In addition to Bayesian estimation, leveraging model-aware RL, it is also possible to find optimal controls for the minimization of the Cramér-Rao bound, based on Fisher information.
Silicon spin qubits are a promising platform for large-scale quantum computing because of their compatibility with advanced semiconductor fabrication technology. However, charge noise remains a major challenge since it causes timedependent drifts in qubit frequency and exchange interactions through electric field fluctuations. These drifts in control parameters are one obstacle to achieving the high-fidelity quantum operations required for quantum error correction. In this work, we propose a Bayesian optimization (BO) framework for the adaptive calibration of quantum gate parameters in silicon qubits. In addition, to address the impact of charge noise, which exhibits a1/f1 / f1/f-like power spectral density, we incorporate a forgetting mechanism into the Gaussian process model used during optimization. Our simulations on a realistic silicon quantum dot system show that BO-based method improves gate fidelity by 0.266% and reduces calibration iterations by 36.9% compared to random search. Compared to standard BO, our modified method achieves a further fidelity gain of 0.008% and a 9.23% reduction in iterations. These results highlight the potential of BO-based calibration for robust quantum gate implementation under realistic noise conditions.
Identifying and calibrating quantitative dynamical models for physical quantum systems is important for a variety of applications. Here we present a closed-loop Bayesian learning algorithm for estimating multiple unknown parameters in a dynamical model, using optimized experimental ``probe'' controls and measurement. The estimation algorithm is based on a Bayesian particle filter, and is designed to autonomously choose informationally optimized probe experiments with which to compare to model predictions. We demonstrate the performance of the algorithm in both simulated calibration tasks and in an experimental single-qubit ion-trap system. Experimentally, we find that, with 606060 times fewer samples, we exceed the precision of conventional calibration methods, delivering an approximately 939393 times improvement in efficiency (as quantified by the reduction of measurements and resets required to achieve a target residual uncertainty and multiplied by the increase in accuracy). In simulated and experimental demonstrations, we see that successively longer pulses are selected as the posterior uncertainty iteratively decreases, leading to an exponential improvement in the accuracy of model parameters with the number of experimental queries, and a commensurate increase in the per-query time.
This document presents a rigorous experimental framework for investigating automatic cal-ibration of superconducting qubits using reinforcement learning (RL). The calibration problemis formulated initially as a partially observable Markov decision process (POMDP), becausethe physical state of the device is not directly observable. A reduced MDP representationmay be used only when the measured state vector is demonstrably sufficient for the selectedcontrol task.The controller receives experimentally accessible observables, selects bounded calibrationactions, and receives a reward constructed from measurable calibration-quality metrics, actioncost, and safety constraints. A digital twin is used for offline training, while the final evaluationis performed on hardware under a frozen evaluation protocol.Version 3.1 introduces explicit separation between training, validation, and evaluation data;a formal sim-to-real analysis; a safety supervisor and deterministic fallback controller; latencyand drift-timescale requirements; preregistered primary and secondary endpoints; paired ex-perimental blocks; cooldown-level clustering; bootstrap and hierarchical statistical analysis;placebo and ablation tests; and reproducibility requirements.The primary endpoint is the difference in time-above-threshold between the RL controllerand a matched baseline controller. The analysis is designed to distinguish genuine adaptivecalibration from improvements caused by resource imbalance, initial-condition differences,reward leakage, hardware drift, or statistical artifacts.No experimental improvement is claimed in this document.