We propose a novel framework for teleportation-mediated non-local gate synthesis by integrating evolutionary learning with a quantum variational autoencoder (QVAE). The conventional approaches to quantum teleportation often rely on static entanglement resources and fixed measurement bases, which limit adaptability and efficiency. The proposed method addresses these limitations through a symmetry-preserving QVAE that dynamically compresses quantum states while preserving teleportation-critical features, combined with an evolutionary optimizer to refine protocol performance. The QVAE employs a parameterized quantum circuit with SU(3)-symmetric layers to encode two-qubit states into a compressed latent representation, then reconstructs them via a Bell-basis measurement decoder. The evolutionary component optimizes a multi-objective fitness function balancing teleportation fidelity and entanglement efficiency, adapting parameters in real-time through Gaussian mutations and annealing. Moreover, the system integrates seamlessly with existing teleportation protocols by replacing traditional Bell-state generation with adaptive state preparation and post-teleportation error correction. Implemented on a superconducting quantum processor with classical co-processing, our framework achieves high fidelity (above 0.99) while reducing classical communication overhead by 50%. The hybrid architecture operates at a 10 kHz update rate, ensuring compatibility with current quantum networking standards without additional hardware requirements. This work demonstrates the potential of evolutionary quantum autoencoders to enhance teleportation-based gate synthesis, offering a scalable and adaptive solution for future quantum communication systems.
We propose a novel framework for teleportation-mediated non-local gate synthesis by integrating evolutionary learning with a quantum variational autoencoder (QVAE). The conventional approaches to quantum teleportation often rely on static entanglement resources and fixed measurement bases, which limit adaptability and efficiency. The proposed method addresses these limitations through a symmetry-preserving QVAE that dynamically compresses quantum states while preserving teleportation-critical features, combined with an evolutionary optimizer to refine protocol performance. The QVAE employs a parameterized quantum circuit with SU(3)-symmetric layers to encode two-qubit states into a compressed latent representation, then reconstructs them via a Bell-basis measurement decoder. The evolutionary component optimizes a multi-objective fitness function balancing teleportation fidelity and entanglement efficiency, adapting parameters in real-time through Gaussian mutations and annealing. Moreover, the system integrates seamlessly with existing teleportation protocols by replacing traditional Bell-state generation with adaptive state preparation and post-teleportation error correction. Implemented on a superconducting quantum processor with classical co-processing, our framework achieves high fidelity (above 0.99) while reducing classical communication overhead by 50%. The hybrid architecture operates at a 10 kHz update rate, ensuring compatibility with current quantum networking standards without additional hardware requirements. This work demonstrates the potential of evolutionary quantum autoencoders to enhance teleportation-based gate synthesis, offering a scalable and adaptive solution for future quantum communication systems.
Multi‐objective optimization in quantum systems poses formidable challenges stemming from the high dimensionality, complex constraints, and conflicting performance metrics inherent to quantum control tasks and circuit synthesis. This study presents a comprehensive exploration of genetic AI algorithms—evolutionary strategies inspired by natural selection—tailored specifically for multi‐objective optimization in quantum computing contexts. We propose a hybrid framework that synergistically combines the elitist, Pareto‐based selection mechanics of NSGA-II with quantum‐inspired crossover and mutation operators designed to preserve entanglement structures and exploit hardware‐specific gate sets. In this framework, candidate solutions encoding circuit topologies or control‐pulse parameters undergo iterative evolution, guided by fitness vectors that balance gate fidelity, circuit depth, and resource overhead. To benchmark performance, we apply the algorithm to canonical quantum computing problems: Fourier transform circuits, QAOA ansätze for MaxCut instances, and random Clifford+T circuits. Through extensive simulation on noise-modelled quantum devices, we evaluate Pareto front coverage, convergence speed, diversity maintenance, and robustness under decoherence. Our results demonstrate that the proposed genetic AI algorithm outperforms classical single‐objective genetic methods and established multi‐objective evolutionary algorithms (e.g., SPEA2) by achieving broader Pareto fronts and faster convergence rates, while maintaining solution diversity. Furthermore, noise-resilience experiments show graceful degradation, indicating practical applicability on near-term quantum hardware. These findings substantiate the potential of evolutionary computation paradigms—augmented with quantum‐inspired operators—to address the intricate trade-off surfaces that define NISQ-era optimization problems, paving the way toward automated quantum circuit design and control parameter tuning for real-world quantum computing applications.
Quantum teleportation have a central role in quantum information science and allows transferring of an unknown quantum state through entanglement and classical communication. Unfortunately, the interaction with external and internal noise severely affects the quality of teleportation and poses limitations on practical applications of quantum communication networks. In this work, instead of conventional Bell teleportation, we introduce a Machine Learned adaptive protocol for optimizing multiple components of Quantum Teleportation in order to achieve higher fidelity in various noise environments. In order to demonstrate the performance of the proposed scheme, we study three different noise models, including bit-flip, amplitude damping, and depolarizing noise, both in case of single-qubit and two-qubit channels. As a result, we observe substantial improvement in the teleportation fidelity in comparison to the classical Bell-state teleportation protocol in certain noise conditions. Furthermore, the machine-learned protocol reveals a nontrivial strategy for compensation of decoherence and information losses. In addition, obtained results indicate the flexibility and reliability of the proposed framework for implementing various adaptive quantum communications while shedding light on possibilities of discovery of optimal quantum algorithms by means of automated approache
Quantum computing (QC) has demonstrated strong theoretical potential for solving complex optimization problems, yet its practical impact depends on the availability of resource-efficient quantum circuits compatible with near-term hardware constraints. In this context, classical artificial intelligence (AI) techniques, particularly evolutionary computation (EC), play a crucial enabling role by enhancing the feasibility and scalability of quantum processes. This work presents a quantum-inspired evolutionary computation framework that leverages classical EC mechanisms to improve quantum circuit synthesis under the Clifford+T gate set. The proposed approach integrates a compact encoding scheme, a knowledge-driven Separation mechanism to resolve functional redundancy, and a dynamic Local Search strategy for phase refinement, demonstrating how classical EC can effectively guide quantum-oriented optimization tasks. Experimental results on diverse benchmark circuits show that the proposed framework achieves higher success rates while significantly reducing computational evaluations compared to state-of-the-art methods, without compromising circuit optimality. Moreover, the resulting optimized circuits provide reusable building blocks for future quantum algorithms, illustrating a concrete and effective instance of QC–EC collaboration within quantum-inspired AI.
The design of autonomous quantum systems constitutes an entirely new paradigm for next-generation computing by having machine intelligence do the engineering work to build and optimise successful quantum architectures. We address the problem of self-optimizing quantum systems that perform adaptive control, circuit synthesis and decision making in both accurate and uncertain controllable environments via a two-pronged approach: Reinforcement Learning (RL) together with Evolutionary Strategies (ES). In this work, we find that reinforcement learning provides a general framework for sequential decision-making, where agents learn optimal policies from reward signals by interacting with quantum environments. Evolutionary strategies, which are based on ideas from biological evolution, provide an alternative to RL by performing global optimization of quantum circuit parameters and architectures using the standard canonical processes of mutation, selection and recombination. Recent developments in quantum technologies show, again, that machine learning tools (ML), especially RL can be very useful to optimize unavailable closed blow-ups related with quantity functions. Moreover, evolutionary optimization based hybrids with RL have demonstrated better performance on the complex multi-objective quantum problems due to balanced exploitation and exploration. In this paper, we provide an overview of a versatile framework for autonomous quantum system design that showcases example algorithmic architectures, hybrid machine learning models and real world applications in areas such as quantum control, quantum circuit synthesis and energy optimization. In addition, we discuss well-known obstacles such as the scalability problem, the noise sensitivity issue, barren plateaus of quantum optimization and computational complexity. Comparisons to traditional methods show that reinforcement learning (RL) when combined with evolutionary strategies enables a significant improvement in efficiency, adaptability, and robustness for quantum system design as supported by experimental studies and case analyses. Future research directions are then discussed, including quantum-native learning algorithms, multi-agent quantum reinforcement learning and hardware-aware optimization techniques
Abstract Quantum teleportation is an elemental process in quantum communication and many variants have been widely investigated theoretically and experimentally. Motivated by cooperation in classical communications, cooperative quantum teleportation (CQT) are developed with features of the cooperation referring to allocation of resources and operations among participants. Parameterized quantum circuit (PQC) are employed to learn the CQT protocols on account of different training scenarios with controls of gate parameters among shared entangled states, measurement, and recovery operations. Numerical results show the CQT protocols can be discovered with unit fidelity regardless of ideal or nonideal channels by training the PQCs with hybrid quantum‐classical (HQC) optimization under full cooperations of the participants. Further, the influence of quantum channel noise on the teleportation performance is explored by parameterizing the entangled states with noise and entanglement parameters under adjustable recovery operations. Simulation results indicate the trained PQC can improve the system performance, which implies the potential denoising capability of the HQC algorithms. The suggested CQT protocols satisfy the underlying properties of universality, randomness, locality and cooperation, and discussions indicate the designed quantum circuits can be optimized in view of quantum and circuit costs by appropriate optimization algorithms for achieving higher state fidelity in the future work.
In recent years, machine learning and deep learning have driven advances in domains such as image classification, speech recognition, and anomaly detection by leveraging multi-layer neural networks to model complex data. Simultaneously, quantum computing (QC) promises to address classically intractable problems via quantum parallelism, motivating research in quantum machine learning (QML). Among QML techniques, quantum autoencoders show promise for compressing high-dimensional quantum and classical data. However, designing effective quantum circuit architectures for quantum autoencoders remains challenging due to the complexity of selecting gates, arranging circuit layers, and tuning parameters.
This paper proposes a neural architecture search (NAS) framework that automates the design of quantum autoencoders using a genetic algorithm (GA). By systematically evolving variational quantum circuit (VQC) configurations, our method seeks to identify high-performing hybrid quantum-classical autoencoders for data reconstruction without becoming trapped in local minima. We demonstrate effectiveness on image datasets, highlighting the potential of quantum autoencoders for efficient feature extraction within a noise-prone, near-term quantum era. Our approach lays a foundation for broader application of genetic algorithms to quantum architecture search, aiming for a robust, automated method that can adapt to varied data and hardware constraints.