Quantum computing is currently strongly limited by the impact of noise, in particular introduced by the application of two-qubit gates. For this reason, reducing the number of two-qubit gates is of paramount importance on noisy intermediate-scale quantum hardware. To advance towards more reliable quantum computing, we introduce a framework based on ZX calculus, graph-neural networks and reinforcement learning for quantum circuit optimization. By combining reinforcement learning and tree search, our method addresses the challenge of selecting optimal sequences of ZX calculus rewrite rules. Instead of relying on existing heuristic rules for minimizing circuits, our method trains a novel reinforcement learning policy that directly operates on ZX-graphs, therefore allowing us to search through the space of all possible circuit transformations to find a circuit significantly minimizing the number of CNOT gates. This way we can scale beyond hard-coded rules towards discovering arbitrary optimization rules. We demonstrate our method's competetiveness with state-of-the-art circuit optimizers and generalization capabilities on large sets of diverse random circuits.
We propose a novel Reinforcement Learning (RL) method for optimizing quantum circuits using graph-theoretic simplification rules of ZX-diagrams. The agent, trained using the Proximal Policy Optimization (PPO) algorithm, employs Graph Neural Networks to approximate the policy and value functions. We demonstrate the capacity of our approach by comparing it against the best performing ZX-Calculus-based algorithm for the problem in hand. After training on small Clifford+T circuits of 5-qubits and few tenths of gates, the agent consistently improves the state-of-the-art for this type of circuits, for at least up to 80-qubit and 2100 gates, whilst remaining competitive in terms of computational performance. Additionally, we illustrate the versatility of the agent by incorporating additional optimization routines on the workflow during training, improving the two-qubit gate count state-of-the-art on multiple structured quantum circuits for relevant applications of much larger dimension and different gate distributions than the circuits the agent trains on. This conveys the potential of tailoring the reward function to the specific characteristics of each application and hardware backend. Our approach is a valuable tool for the implementation of quantum algorithms in the near-term intermediate-scale range (NISQ).
Abstract ZX-diagrams are a powerful graphical language for the description of quantum processes with applications in fundamental quantum mechanics, quantum circuit optimization, tensor network simulation, and many more. The utility of ZX-diagrams relies on a set of local transformation rules that can be applied to them without changing the underlying quantum process they describe. These rules can be exploited to optimize the structure of ZX-diagrams for a range of applications. However, finding an optimal sequence of transformation rules is generally an open problem. In this work, we bring together ZX-diagrams with reinforcement learning, a machine learning technique designed to discover an optimal sequence of actions in a decision-making problem and show that a trained reinforcement learning agent can significantly outperform other optimization techniques like a greedy strategy, simulated annealing, and state-of-the-art hand-crafted algorithms. The use of graph neural networks to encode the policy of the agent enables generalization to diagrams much bigger than seen during the training phase.
Quantum computers allow a near-exponential speed-up for specific applications when compared to classical computers. Despite recent advances of quantum computing hardware, the practical use of NISQ era devices remains severely limited due to resources constraints (e.g., noise, qubits, gates, circuit depth, and coherence time). QC optimization is an essential mitigation strategy to enable the execution of quantum programs on restricted quantum devices. In this context, ZX-calculus emerged as an alternative to conventional gate-level QC optimization approaches. Instead of depending upon gate set specific rewriting rules, it offers a compact, universal and semantics-preserving framework for QC optimization. However, ZX-based QC optimization faces two challenges in practice. On the one hand, ZX-calculus admits a non-terminating rewriting system. On the other hand, ZX-diagrams lose causality. As a consequence, only a subset of ZX-diagrams that preserve CFlow, GFlow or Pauli flow allow for the extraction of QCs in polynomial-time. The first challenge can be addressed by effective heuristics, search algorithms and pruning conditions while the latter is an optimization problem with an upper bound of
NPNP#P, where the choice of the extraction algorithm can negate ZX-diagram level improvements. This thesis establishes a ZX-based end-to-end pipeline for QC optimization that leverages tree search for metric-agnostic ZX-diagram optimization and \gls{ilp} paired with backtracking search to improve the circuit extraction step. The contributions of this thesis are four-fold: (i) First, it presents a comprehensive survey of ZX-based QC optimization, categorizing them by the employed optimization strategy, the target metric, and the intended quantum computing architecture. (ii) Second, this work formalizes the ZX-diagram optimization problem as the explicit state-space exploration of rewriting rule sequences. (iii) Thirdly, the formal approach is put into practice by implementing tree search algorithms, in particular DFS, IDDFS, and LDS, to reduce the T-gate, and Edge count of ZX-diagrams. Furthermore, the efficacy of different pruning conditions are investigated. Lastly, the novel Local-Elimination (LE) is introduced as a metaheuristic to select growing sub ZX-diagrams around a target spider. Instead of performing tree search optimization on intractable large ZX-diagrams, LE changes one large optimization problem into a sequence of tractable small searches. All tree search strategies are extensively tested on benchmark data sets that contain different QC types. (iv) Finally, this work enhances two-qubit gate count during circuit extraction by introducing an ILP model that replaces the Gaussian Elimination steps present in current circuit extraction algorithms. Pairing the ILP model for circuit extraction with backtracking allows the exploration of multiple solutions that take advantage of gate commutation and cancellation rules during extraction. The last research artifact of this thesis is the introduction of \emph{ZX-benchmark}, a declarative end-to-end optimization pipeline and ZX benchmarking framework to compare different optimization and extraction algorithms on the same data sets and under comparable experimental conditions. To this end, it offers access to multiple data sets, and various third-party optimizers. With the intent to offer a framework that is useful beyond the scope of this thesis, the framework provides support of configuration files and a unified API to declare experiments. All artifacts produced are in the form of plain text formats (JSON, and OpenQASM). In summary, the thesis advances ZX-based compilation by connecting metric-agnostic diagram rewriting with extraction-aware optimization in a reusable, end-to-end workflow.
Quantum circuit optimization is a foundational challenge in realizing practical quantum computation, requiring the reduction of gate counts and circuit depth while preserving logical equivalence across noisy intermediate-scale quantum (NISQ) devices. Conventional rule-based and heuristic compilation approaches demonstrate diminishing effectiveness as circuit complexity grows, motivating the search for adaptive, data-driven alternatives. This paper reformulates quantum circuit optimization as a Markov decision process (MDP), enabling deep reinforcement learning (RL) agents to autonomously discover efficient transformation strategies. A graph neural network (GNN)-based actor-critic architecture is developed to encode circuit topology and guide transformation selection. Drawing on empirical evidence from phase-structured quantum control tasks, neural feedback architectures, and convergence behavior in active learning agents, we demonstrate that the proposed framework achieves an average two-qubit gate count reduction of 31.4% and a circuit depth reduction of 27.8% across standard benchmark circuits, outperforming established compilation baselines. This work provides a principled theoretical foundation for the RL-as-optimizer paradigm and contributes an extensible experimental platform suited to NISQ-era constraints.
The practical implementation of quantum algorithms on noisy intermediate-scale quantum devices encounters operational limitations due to decoherence and other sources of noise inherent in real hardware. To mitigate these errors while preserving the original functionality of the algorithm, shorter quantum circuits are therefore preferred. This motivates the development of effective quantum circuit optimization algorithms. Learning-based approaches have emerged as a leading candidate, yet existing autonomous agents remain inefficient, spending most of their training capacity rediscovering elementary reductions that deterministic rule-based methods already handle reliably. To address this challenge, we propose a reinforcement learning framework that embeds a deterministic Commutation-and-Reduction (CR) algorithm directly into the training environment. After every agent action, the CR algorithm automatically resolves elementary commutations and cancellations, enabling the agent to focus its learning capacity on the non-trivial optimizations where reinforcement learning adds real value. Empirical evaluation across two gate sets, the universal Clifford+T basis and the CNOT+Pauli basis, shows that RL+CR produces shorter circuits than a standard RL agent at all tested scales. We demonstrate that RL trained on smaller quantum circuits can be applied to larger quantum circuits. On 20-qubit Clifford+T circuits, five times larger than the training circuits, RL+CR removes twice as many gates as standard RL. This work provides a robust approach that could accelerate the compilation and optimization processes for future fault-tolerant and utility-scale quantum systems.
Quantum computing is an emerging technology in which quantum mechanical properties are suitably utilized to perform certain compute-intensive operations faster than classical computers. Quantum algorithms are designed as a combination of quantum circuits that each require a large number of quantum gates, which is a challenge considering the limited number of qubit resources available in quantum computing systems. Our work proposes a technique to optimize quantum arithmetic algorithms by reducing the hardware resources and the number of qubits based on ZX calculus. We have utilised ZX calculus rewrite rules for the optimization of fault-tolerant quantum multiplier circuits where we are able to achieve a significant reduction in the number of ancilla bits and T-gates as compared to the originally required numbers to achieve fault-tolerance. Our work is the first step in the series of arithmetic circuit optimization using graphical rewrite tools and it paves the way for advancing the optimization of various complex quantum circuits and establishing the potential for new applications of the same.