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

arXiv:2607.22468

Learning to Prepare Molecular Ground States with Transformer Models

Alex Koziell-Pipe, Jasmine Brewer, Jem Guhit, Marwa H. Farag, Kripa Panchagnula, Gabriel Laude, Fabian Finger, Carlo Gaggioli, Ludmila Szulakowska, Oliver J. Backhouse, Christos Papalitsas, Jason G. Mustakis, Thomas Soini, David Munoz Ramo, Stephen Clark, Elica Kyoseva, Enrico Rinaldi

quant-phcs.AISubmitted Jul 24, 2026• Announced Jul 27, 2026• 2 citations
arXivHTMLPDF

Abstract

Quantum state preparation is a key component of many quantum algorithms. Performing this step efficiently is essential for realizing practical quantum advantage in quantum chemistry applications. Iterative algorithms like ADAPT-VQE can produce shallow ground-state preparation circuits, but become computationally prohibitive for the larger molecules relevant to materials science and pharmaceutical development. Here, we introduce ADAPT-GQE, a generative AI framework that learns to synthesize ground-state preparation circuits for electronic structure calculations. We first use ADAPT-VQE to generate high-quality reference circuits, which are then used as targets for training models for circuit generation. Once trained, the model can efficiently propose and score circuits, enabling reinforcement learning (RL) to drive circuit generation accuracy beyond the accuracy of the ADAPT-VQE training data. This pipeline achieves order-of-magnitude reductions in circuit generation time relative to ADAPT-VQE while maintaining comparable or improved state-preparation accuracy. We demonstrate ADAPT-GQE on imipramine, a well-established tricyclic antidepressant that serves as a representative, challenging target for computational modelling in drug stability protocols. We execute generated circuits on Quantinuum Helios-1, representing a milestone for AI-generated quantum chemistry circuits on state-of-the-art quantum hardware. These results establish a pathway toward automated quantum circuit synthesis for utility-scale quantum computational chemistry.

Related papers

Benchmarking Adaptive Quantum Circuit Optimization Algorithms for Quantum Chemistry

Waheeda Saib, Xavier Bonet-Monroig, Vedran Dunjko +3 more

In the noisy near-term quantum computing era variational quantum algorithms are promising to explore the boundaries of quantum advantage. One prevalent instance is the variational quantum eigensolver (VQE) employed in quantum chemistry to approximate ground-state energies of molecules. The performance of VQE depends on the design of the parametrized quantum circuit, as well as the optimization algorithm used to optimize those parameters. Circuit optimization methods have been developed to generate quantum circuits to reach accurate approximations to the ground-states. In this work, we conduct an empirical comparison between two prominent adaptive quantum circuit optimization algorithms, namely qubit-ADAPT-VQE and a reinforcement learning (RL) based method, on the problem of finding the ground state energy of Lithium Hydride (LiH). In our experiment, we focus on the circuit depth generated by each circuit optimization method and the number of two-qubit quantum gates in the best-found circuit.

IEEE International Conference on Quantum Computing and Engineering (QCE)•Sep 17, 2023•2 citations

Generative quantum eigensolver with constrained circuit-cutting overhead

Junya Nakamura, Shinichiro Sanji

Generative quantum eigensolver (GQE) is a hybrid quantum-classical algorithm that iteratively trains a classical generative machine learning model such that the model can generate quantum circuits with desired properties such as approximating molecular ground states. It offers as many potential applications and as much flexibility as variational quantum eigensolvers, while avoiding the problem of barren plateaus. Quantum circuit cutting (QCC) is a technique to perform quantum computations that require more qubits than available on single quantum devices. It comes with considerable sampling overhead depending on the structure of the circuit to be cut and how the circuit is cut. To make QCC practical, therefore, the circuits to be cut must be designed such that their execution is meaningful and QCC overhead is kept small. In this work, we extend GQE such that the generative model only produces circuits whose overhead by QCC is upper-bounded, while retaining the original purpose of GQE. Consequently, our proposal not only enhances the applicability of GQE through the use of QCC, but also provides a practical application for QCC. Using a transformer decoder implementation of GQE, we evaluate our method through simulated ground state search experiments on the BeH_2 molecule. A new loss function and a hybrid online/offline training strategy are also introduced and it is observed that these tools improve convergence and final energy values.

arXiv:2509.08351•Sep 10, 2025•2 citations

The generative quantum eigensolver (GQE) and its application for ground state search

Kouhei Nakaji, Lasse Bjørn Kristensen, Kemmoku, Ryota +14 more

We introduce the generative quantum eigensolver (GQE), a new quantum computational framework that operates outside the variational quantum algorithm paradigm by applying classical generative models to quantum simulation. The GQE algorithm optimizes a classical generative model to produce quantum circuits with desired properties. Here, we develop a transformer-based implementation, which we name the generative pre-trained transformer-based (GPT) quantum eigensolver (GPT-QE). We show a proof-of-concept of training and pretraining of GPT-QE applied to electronic structure Hamiltonians, and demonstrate its ability illustrated by surpassing coupled cluster singles and doubles (CCSD) for the strong bond dissociation of the nitrogen molecule and approaching chemical accuracy. We also demonstrate the method on real quantum hardware.

arXiv:2401.09253•Jan 17, 2024•79 citations

Reinforcement learning of quantum circuit architectures for molecular potential energy curves

Maureen Krumtünger, Alissa Wilms, Paul K. Faehrmann +4 more

Quantum chemistry and optimization are two of the most prominent applications of quantum computers. Variational quantum algorithms have been proposed for solving problems in these domains. However, the design of the quantum circuit ansatz remains a challenge. Of particular interest is developing a method to generate circuits for any given instance of a problem, not merely a circuit tailored to a specific instance of the problem. To this end, we present a reinforcement learning (RL) approach to learning a problem-dependent quantum circuit mapping, which outputs a circuit for the ground state of a Hamiltonian from a given family of parameterized Hamiltonians. For quantum chemistry, our RL framework takes as input a molecule and a discrete set of bond distances, and it outputs a bond-distance-dependent quantum circuit for arbitrary bond distances along the potential energy curve. The inherently non-greedy approach of our RL method contrasts with existing greedy approaches to adaptive, problem-tailored circuit constructions. We demonstrate its effectiveness for the four-qubit and six-qubit lithium hydride molecules, as well as an eight-qubit H$_4$ chain. Our learned circuits are interpretable in a physically meaningful manner, thus paving the way for applying RL to the development of novel quantum circuits for the ground states of large-scale molecular systems.

quant-pharXiv:2511.16559•Nov 21, 2025•2 citations

Hybrid reward-driven reinforcement learning for efficient quantum circuit synthesis

Sara Giordano, Kornikar Sen, Miguel Angel Martin-Delgado

A reinforcement learning (RL) framework is introduced for the efficient synthesis of quantum circuits that generate specified target quantum states from a fixed initial state, addressing a central challenge in both the Noisy Intermediate-Scale Quantum (NISQ) era and future fault-tolerant quantum computing. The approach utilizes tabular Q-learning, based on action sequences, within a discretized quantum state space, to effectively manage the exponential growth of the space dimension. The framework introduces a hybrid reward mechanism, combining a static, domain-informed reward that guides the agent toward the target state with customizable dynamic penalties that discourage inefficient circuit structures such as gate congestion and redundant state revisits. This is a circuit-aware reward, in contrast to the current trend of works on this topic, which are primarily fidelity-based. By leveraging sparse matrix representations and state-space discretization, the method enables practical navigation of high-dimensional environments while minimizing computational overhead. Benchmarking on graph-state preparation tasks for up to seven qubits, we demonstrate that the algorithm consistently discovers minimal-depth circuits with optimized gate counts. Moreover, extending the framework to a universal gate set still yields low depth circuits, highlighting the algorithm’s robustness and adaptability. The results confirm that this RL-driven approach, with our completely circuit-aware method, efficiently explores the complex quantum state space and synthesizes near-optimal quantum circuits, providing a resource-efficient foundation for quantum circuit optimization.

arXiv:2507.16641•Quantum Machine Intelligence•Feb 3, 2026•4 citations

Quantum Algorithms for Drug Discovery and Molecular Simulation

Marta Ivanov, Nina Muller, Oscar Hansen

Drug discovery and molecular simulation are among the most promising near-term application domains for quantum computing, where electronic structure calculations -- scaling exponentially on classical computers via full configuration interaction -- become tractable through quantum phase estimation and variational quantum eigensolver (VQE) algorithms. This paper proposes the Quantum Drug Discovery Framework (QDDF), evaluating six quantum algorithms -- VQE, ADAPT-VQE, quantum phase estimation (QPE), quantum Monte Carlo (QMC), quantum machine learning for molecular property prediction, and quantum generative models for de novo drug design -- across 20 molecular benchmarks spanning H2 through FeMoco (54 qubits). Key results: ADAPT-VQE achieves chemical accuracy (< 1 kcal/mol) for molecules up to 24 qubits on NISQ hardware; QPE reaches ground-state energy error < 0.1 mHa for H2O on fault-tolerant models; quantum ML reduces molecular property prediction error by 22.4% versus classical graph neural networks. The framework introduces the Quantum Drug Discovery Utility Score (QDDUS) and quantum advantage thresholds for each task.

Quantum Frontiers Journal•Nov 12, 2025•0 citations
Quantum state preparation is a key component of many quantum algorithms. Performing this step efficiently is essential for realizing practical quantum advantage in quantum chemistry applications. Iterative algorithms like ADAPT-VQE can produce shallow ground-state preparation circuits, but become computationally prohibitive for the larger molecules relevant to materials science and pharmaceutical development. Here, we introduce ADAPT-GQE, a generative AI framework that learns to synthesize ground-state preparation circuits for electronic structure calculations. We first use ADAPT-VQE to generate high-quality reference circuits, which are then used as targets for training models for circuit generation. Once trained, the model can efficiently propose and score circuits, enabling reinforcement learning (RL) to drive circuit generation accuracy beyond the accuracy of the ADAPT-VQE training data. This pipeline achieves order-of-magnitude reductions in circuit generation time relative to ADAPT-VQE while maintaining comparable or improved state-preparation accuracy. We demonstrate ADAPT-GQE on imipramine, a well-established tricyclic antidepressant that serves as a representative, challenging target for computational modelling in drug stability protocols. We execute generated circuits on Quantinuum Helios-1, representing a milestone for AI-generated quantum chemistry circuits on state-of-the-art quantum hardware. These results establish a pathway toward automated quantum circuit synthesis for utility-scale quantum computational chemistry.
In the noisy near-term quantum computing era variational quantum algorithms are promising to explore the boundaries of quantum advantage. One prevalent instance is the variational quantum eigensolver (VQE) employed in quantum chemistry to approximate ground-state energies of molecules. The performance of VQE depends on the design of the parametrized quantum circuit, as well as the optimization algorithm used to optimize those parameters. Circuit optimization methods have been developed to generate quantum circuits to reach accurate approximations to the ground-states. In this work, we conduct an empirical comparison between two prominent adaptive quantum circuit optimization algorithms, namely qubit-ADAPT-VQE and a reinforcement learning (RL) based method, on the problem of finding the ground state energy of Lithium Hydride (LiH). In our experiment, we focus on the circuit depth generated by each circuit optimization method and the number of two-qubit quantum gates in the best-found circuit.
Generative quantum eigensolver (GQE) is a hybrid quantum-classical algorithm that iteratively trains a classical generative machine learning model such that the model can generate quantum circuits with desired properties such as approximating molecular ground states. It offers as many potential applications and as much flexibility as variational quantum eigensolvers, while avoiding the problem of barren plateaus. Quantum circuit cutting (QCC) is a technique to perform quantum computations that require more qubits than available on single quantum devices. It comes with considerable sampling overhead depending on the structure of the circuit to be cut and how the circuit is cut. To make QCC practical, therefore, the circuits to be cut must be designed such that their execution is meaningful and QCC overhead is kept small. In this work, we extend GQE such that the generative model only produces circuits whose overhead by QCC is upper-bounded, while retaining the original purpose of GQE. Consequently, our proposal not only enhances the applicability of GQE through the use of QCC, but also provides a practical application for QCC. Using a transformer decoder implementation of GQE, we evaluate our method through simulated ground state search experiments on the BeH_2 molecule. A new loss function and a hybrid online/offline training strategy are also introduced and it is observed that these tools improve convergence and final energy values.
We introduce the generative quantum eigensolver (GQE), a new quantum computational framework that operates outside the variational quantum algorithm paradigm by applying classical generative models to quantum simulation. The GQE algorithm optimizes a classical generative model to produce quantum circuits with desired properties. Here, we develop a transformer-based implementation, which we name the generative pre-trained transformer-based (GPT) quantum eigensolver (GPT-QE). We show a proof-of-concept of training and pretraining of GPT-QE applied to electronic structure Hamiltonians, and demonstrate its ability illustrated by surpassing coupled cluster singles and doubles (CCSD) for the strong bond dissociation of the nitrogen molecule and approaching chemical accuracy. We also demonstrate the method on real quantum hardware.
Quantum chemistry and optimization are two of the most prominent applications of quantum computers. Variational quantum algorithms have been proposed for solving problems in these domains. However, the design of the quantum circuit ansatz remains a challenge. Of particular interest is developing a method to generate circuits for any given instance of a problem, not merely a circuit tailored to a specific instance of the problem. To this end, we present a reinforcement learning (RL) approach to learning a problem-dependent quantum circuit mapping, which outputs a circuit for the ground state of a Hamiltonian from a given family of parameterized Hamiltonians. For quantum chemistry, our RL framework takes as input a molecule and a discrete set of bond distances, and it outputs a bond-distance-dependent quantum circuit for arbitrary bond distances along the potential energy curve. The inherently non-greedy approach of our RL method contrasts with existing greedy approaches to adaptive, problem-tailored circuit constructions. We demonstrate its effectiveness for the four-qubit and six-qubit lithium hydride molecules, as well as an eight-qubit H4_44​ chain. Our learned circuits are interpretable in a physically meaningful manner, thus paving the way for applying RL to the development of novel quantum circuits for the ground states of large-scale molecular systems.
A reinforcement learning (RL) framework is introduced for the efficient synthesis of quantum circuits that generate specified target quantum states from a fixed initial state, addressing a central challenge in both the Noisy Intermediate-Scale Quantum (NISQ) era and future fault-tolerant quantum computing. The approach utilizes tabular Q-learning, based on action sequences, within a discretized quantum state space, to effectively manage the exponential growth of the space dimension. The framework introduces a hybrid reward mechanism, combining a static, domain-informed reward that guides the agent toward the target state with customizable dynamic penalties that discourage inefficient circuit structures such as gate congestion and redundant state revisits. This is a circuit-aware reward, in contrast to the current trend of works on this topic, which are primarily fidelity-based. By leveraging sparse matrix representations and state-space discretization, the method enables practical navigation of high-dimensional environments while minimizing computational overhead. Benchmarking on graph-state preparation tasks for up to seven qubits, we demonstrate that the algorithm consistently discovers minimal-depth circuits with optimized gate counts. Moreover, extending the framework to a universal gate set still yields low depth circuits, highlighting the algorithm’s robustness and adaptability. The results confirm that this RL-driven approach, with our completely circuit-aware method, efficiently explores the complex quantum state space and synthesizes near-optimal quantum circuits, providing a resource-efficient foundation for quantum circuit optimization.
Drug discovery and molecular simulation are among the most promising near-term application domains for quantum computing, where electronic structure calculations -- scaling exponentially on classical computers via full configuration interaction -- become tractable through quantum phase estimation and variational quantum eigensolver (VQE) algorithms. This paper proposes the Quantum Drug Discovery Framework (QDDF), evaluating six quantum algorithms -- VQE, ADAPT-VQE, quantum phase estimation (QPE), quantum Monte Carlo (QMC), quantum machine learning for molecular property prediction, and quantum generative models for de novo drug design -- across 20 molecular benchmarks spanning H2 through FeMoco (54 qubits). Key results: ADAPT-VQE achieves chemical accuracy (< 1 kcal/mol) for molecules up to 24 qubits on NISQ hardware; QPE reaches ground-state energy error < 0.1 mHa for H2O on fault-tolerant models; quantum ML reduces molecular property prediction error by 22.4% versus classical graph neural networks. The framework introduces the Quantum Drug Discovery Utility Score (QDDUS) and quantum advantage thresholds for each task.