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:2602.04072

Data Verification is the Future of Quantum Computing Copilots

Junhao Song, Ziqian Bi, Xinliang Chia, William Knottenbelt, Yudong Cao

quant-phSubmitted Feb 3, 2026• Announced Feb 5, 2026• 2 citations
arXivHTMLPDF

Abstract

Quantum program generation demands a level of precision that may not be compatible with the statistical reasoning carried out in the inference of large language models (LLMs). Hallucinations are mathematically inevitable and not addressable by scaling, which leads to infeasible solutions. We argue that architectures prioritizing verification are necessary for quantum copilots and AI automation in domains governed by constraints. Our position rests on three key points: verified training data enables models to internalize precise constraints as learned structures rather than statistical approximations; verification must constrain generation rather than filter outputs, as valid designs occupy exponentially shrinking subspaces; and domains where physical laws impose correctness criteria require verification embedded as architectural primitives. Early experiments showed LLMs without data verification could only achieve a maximum accuracy of 79% in circuit optimization. Our positions are formulated as quantum computing and AI4Research community imperatives, calling for elevating verification from afterthought to architectural foundation in AI4Research.

Comments
13 Pages, 20 Figures. Accepted to AAAI 2026 Workshop on AI4Research. Comments welcome

Related papers

Position: Quantum Program Generation Must Prioritize Validity Over Probabilistic Scaling

Junhao Song, Yu Zhou, William Knottenbelt +1 more

The scaling hypothesis assumes that increasing model parameters yields emergent reasoning capabilities. This position paper argues that applying this probabilistic paradigm to generic quantum circuit synthesis is a directional error. Unlike natural languages, quantum circuits require strict adherence to mathematical constraints that manifest a significant syntax-semantics gap. Training on unverified quantum programs means that models learn syntax but fail to capture the physical semantics of the Hilbert space. Since the valid subset of circuit designs decays exponentially with the number of qubits, post-hoc filtering is mathematically intractable. We propose a pivot from human-centric copilots to verifier-centric agents. We integrate hierarchical constraints, topological masks, and symbolic proxies directly into generation. Our analysis suggests that scale alone cannot bridge the validity gap. Verification-aware architectures offer a viable path for modular quantum program generation. These considerations point toward generation methods that encode task-specific rules of quantum information, rather than relying on imitation alone.

arXiv:2607.15313•Jul 15, 2026•1 citation

Ethical Considerations of LLM-Driven Quantum Code Generation for Optimization Tasks

Independent Researcher , USA, Jyoti Kunal Shah

The convergence of large language models (LLMs) and quantum computing has the potential to revolutionize software development for quantum optimization tasks. AI-assisted code generation, powered by models like OpenAI Codex, can accelerate the design of quantum algorithms by automating routine coding tasks and democratizing access to quantum programming. However, this innovation introduces a web of ethical, legal, and technical challenges. This paper investigates the implications of using LLMs to generate quantum code, focusing on intellectual property (IP) concerns, the risk of unintended outcomes, legal ambiguity, and dual-use scenarios. We propose an ethical architecture for responsible AI-assisted development, incorporating human-in-the-loop systems, license-compliance mechanisms, and auditing tools. Case studies illustrate potential failures in code correctness, security, and attribution. We conclude with recommendations for explainable AI systems, curated datasets, and governance models that ensure innovation without sacrificing safety or compliance. By addressing these concerns proactively, the community can guide LLM-powered quantum development toward a responsible future.

The American Journal of Engineering And Technology•Dec 27, 2023•12 citations

QuantumQA: Enhancing Scientific Reasoning via Physics-Consistent Dataset and Verification-Aware Reinforcement Learning

Songxin Qu, Tai-Ping Sun, Yun-Jie Wang +8 more

Large language models (LLMs) show strong capabilities in general reasoning but typically lack reliability in scientific domains like quantum mechanics, which demand strict adherence to physical constraints. This limitation arises from the scarcity of verifiable training resources and the inadequacy of coarse feedback signals in standard alignment paradigms. To address the data challenge, we introduce QuantumQA, a large-scale dataset constructed via a task-adaptive strategy and a hybrid verification protocol that combines deterministic solvers with semantic auditing to guarantee scientific rigor. Building on this foundation, we propose the verification-aware reward model (VRM) tailored for Reinforcement Learning with Verifiable Rewards (RLVR), which employs an adaptive reward fusion (ARF) mechanism to dynamically integrate deterministic signals from a scientific execution suite (SES) with multidimensional semantic evaluations for precise supervision. Experimental results demonstrate that our method consistently outperforms baselines and general-purpose preference models. Notably, our optimized 8B model achieves performance competitive with proprietary models, validating that incorporating verifiable, rule-based feedback into the reinforcement learning loop offers a parameter-efficient alternative to pure scaling.

cs.AICross-listedarXiv:2604.18176•Apr 21, 2026

Quantum Circuit Verification - A Potential Roadmap (Invited Talk)

Abdulla, Parosh Aziz, Chen, Yu-Fang, Hečko, Michal +4 more

Quantum technologies are progressing at an extraordinary pace and are poised to transform numerous sectors both nationally and globally. Among them, quantum computing stands out for its potential to revolutionize areas such as cryptography, optimization, and the simulation of quantum systems, offering dramatic speed-ups for specific classes of problems. As quantum devices evolve and become increasingly pervasive, guaranteeing their correctness is of paramount importance. This necessitates the development of rigorous methods and tools to analyze and verify their behavior. However, the construction of such verification frameworks presents fundamental challenges. Quantum phenomena such as superposition and entanglement give rise to computational behaviors that differ profoundly from those of classical systems, leading to inherently probabilistic models and exponentially large state spaces, even for relatively small programs. Addressing these challenges requires building on the extensive expertise of the formal methods community in classical program verification, while incorporating recent advances and collaborative efforts in quantum systems. An interesting challenge for the verification community is to design and implement novel verification frameworks that transfer the key strengths of classical verification, such as expressive specification, precise error detection, automation, and scalability, to the quantum domain. We expect that the results of this research will play a crucial role in enabling the dependable deployment of quantum technologies across a wide range of future applications.

Leibniz international proceedings in informatics•Jan 1, 2025•0 citations

Benchmarking the Benchmarks for Quantum Code Generation with LLMs

Yunhe Feng, Xiaokun Yang, Kewei Sha +1 more

Large Language Models (LLMs) are increasingly deployed as quantum coding copilots, assisting researchers by generating complex programs for frameworks such as Qiskit, PennyLane, and OpenQASM. However, accurately evaluating the practical utility of these models remains a significant challenge. Existing benchmarks are highly fragmented, ranging from syntax-centric unit tests to simulator- and hardware-aware metrics, making results difficult to compare across different languages and hardware targets. To address this fragmentation, this paper systematically reviews recent evaluation suites and post-training methodologies for quantum code generation. We distill current evaluation criteria into four practical dimensions: syntax and API validity, semantic and physical correctness, resource and hardware feasibility, and execution-based feedback. Building upon these dimensions, we present a unified taxonomy that maps current benchmarks to emerging model adaptation techniques, specifically retrieval-augmented generation (RAG), fine-tuning, multi-agent workflows, and reinforcement learning (RL). Our analysis highlights a clear shift: moving away from prompt-only baselines and toward agentic workflows driven by quantum-verifiable rewards. This shift directly targets the semantic gap between superficially compilable code and physically executable quantum programs. In addition, we identify key research opportunities-such as standardized semantic metrics and integration with quantum error correction-aimed at fostering a more reproducible, verifiable, and hardware-grounded ecosystem for automated quantum software development.

IEEE Dallas Circuits and Systems Conference (DCAS)•Apr 10, 2026•0 citations

Quantum Computing Meets Large Language Models: Insights, Challenges, and Future Directions

Thippa Reddy Gadekallu, Kai Fang, Hailin Feng +7 more

Large Language Models (LLMs) such as GPT and LLaMA have transformed artificial intelligence, but their rapid growth has brought major challenges in computation, energy use, and scalability. Quantum computing (QC) offers a fundamentally different way to process information, with the potential to accelerate key operations in training, inference, optimization, and representation learning. This survey provides a structured and comprehensive review of how QC can support the future development of LLMs. It examines quantum algorithms, hybrid quantum-classical methods, quantum neural networks, quantum embeddings, and security applications. It also evaluates their feasibility in both the current noisy intermediate-scale quantum (NISQ) era and the future fault-tolerant era. The survey highlights current progress, identifies major technical barriers, and outlines practical research directions needed to build scalable, efficient, and secure quantum-enhanced language models.

•Feb 2, 2026•0 citations
Quantum program generation demands a level of precision that may not be compatible with the statistical reasoning carried out in the inference of large language models (LLMs). Hallucinations are mathematically inevitable and not addressable by scaling, which leads to infeasible solutions. We argue that architectures prioritizing verification are necessary for quantum copilots and AI automation in domains governed by constraints. Our position rests on three key points: verified training data enables models to internalize precise constraints as learned structures rather than statistical approximations; verification must constrain generation rather than filter outputs, as valid designs occupy exponentially shrinking subspaces; and domains where physical laws impose correctness criteria require verification embedded as architectural primitives. Early experiments showed LLMs without data verification could only achieve a maximum accuracy of 79% in circuit optimization. Our positions are formulated as quantum computing and AI4Research community imperatives, calling for elevating verification from afterthought to architectural foundation in AI4Research.
The scaling hypothesis assumes that increasing model parameters yields emergent reasoning capabilities. This position paper argues that applying this probabilistic paradigm to generic quantum circuit synthesis is a directional error. Unlike natural languages, quantum circuits require strict adherence to mathematical constraints that manifest a significant syntax-semantics gap. Training on unverified quantum programs means that models learn syntax but fail to capture the physical semantics of the Hilbert space. Since the valid subset of circuit designs decays exponentially with the number of qubits, post-hoc filtering is mathematically intractable. We propose a pivot from human-centric copilots to verifier-centric agents. We integrate hierarchical constraints, topological masks, and symbolic proxies directly into generation. Our analysis suggests that scale alone cannot bridge the validity gap. Verification-aware architectures offer a viable path for modular quantum program generation. These considerations point toward generation methods that encode task-specific rules of quantum information, rather than relying on imitation alone.
The convergence of large language models (LLMs) and quantum computing has the potential to revolutionize software development for quantum optimization tasks. AI-assisted code generation, powered by models like OpenAI Codex, can accelerate the design of quantum algorithms by automating routine coding tasks and democratizing access to quantum programming. However, this innovation introduces a web of ethical, legal, and technical challenges. This paper investigates the implications of using LLMs to generate quantum code, focusing on intellectual property (IP) concerns, the risk of unintended outcomes, legal ambiguity, and dual-use scenarios. We propose an ethical architecture for responsible AI-assisted development, incorporating human-in-the-loop systems, license-compliance mechanisms, and auditing tools. Case studies illustrate potential failures in code correctness, security, and attribution. We conclude with recommendations for explainable AI systems, curated datasets, and governance models that ensure innovation without sacrificing safety or compliance. By addressing these concerns proactively, the community can guide LLM-powered quantum development toward a responsible future.
Large language models (LLMs) show strong capabilities in general reasoning but typically lack reliability in scientific domains like quantum mechanics, which demand strict adherence to physical constraints. This limitation arises from the scarcity of verifiable training resources and the inadequacy of coarse feedback signals in standard alignment paradigms. To address the data challenge, we introduce QuantumQA, a large-scale dataset constructed via a task-adaptive strategy and a hybrid verification protocol that combines deterministic solvers with semantic auditing to guarantee scientific rigor. Building on this foundation, we propose the verification-aware reward model (VRM) tailored for Reinforcement Learning with Verifiable Rewards (RLVR), which employs an adaptive reward fusion (ARF) mechanism to dynamically integrate deterministic signals from a scientific execution suite (SES) with multidimensional semantic evaluations for precise supervision. Experimental results demonstrate that our method consistently outperforms baselines and general-purpose preference models. Notably, our optimized 8B model achieves performance competitive with proprietary models, validating that incorporating verifiable, rule-based feedback into the reinforcement learning loop offers a parameter-efficient alternative to pure scaling.
Quantum technologies are progressing at an extraordinary pace and are poised to transform numerous sectors both nationally and globally. Among them, quantum computing stands out for its potential to revolutionize areas such as cryptography, optimization, and the simulation of quantum systems, offering dramatic speed-ups for specific classes of problems. As quantum devices evolve and become increasingly pervasive, guaranteeing their correctness is of paramount importance. This necessitates the development of rigorous methods and tools to analyze and verify their behavior. However, the construction of such verification frameworks presents fundamental challenges. Quantum phenomena such as superposition and entanglement give rise to computational behaviors that differ profoundly from those of classical systems, leading to inherently probabilistic models and exponentially large state spaces, even for relatively small programs. Addressing these challenges requires building on the extensive expertise of the formal methods community in classical program verification, while incorporating recent advances and collaborative efforts in quantum systems. An interesting challenge for the verification community is to design and implement novel verification frameworks that transfer the key strengths of classical verification, such as expressive specification, precise error detection, automation, and scalability, to the quantum domain. We expect that the results of this research will play a crucial role in enabling the dependable deployment of quantum technologies across a wide range of future applications.
Large Language Models (LLMs) are increasingly deployed as quantum coding copilots, assisting researchers by generating complex programs for frameworks such as Qiskit, PennyLane, and OpenQASM. However, accurately evaluating the practical utility of these models remains a significant challenge. Existing benchmarks are highly fragmented, ranging from syntax-centric unit tests to simulator- and hardware-aware metrics, making results difficult to compare across different languages and hardware targets. To address this fragmentation, this paper systematically reviews recent evaluation suites and post-training methodologies for quantum code generation. We distill current evaluation criteria into four practical dimensions: syntax and API validity, semantic and physical correctness, resource and hardware feasibility, and execution-based feedback. Building upon these dimensions, we present a unified taxonomy that maps current benchmarks to emerging model adaptation techniques, specifically retrieval-augmented generation (RAG), fine-tuning, multi-agent workflows, and reinforcement learning (RL). Our analysis highlights a clear shift: moving away from prompt-only baselines and toward agentic workflows driven by quantum-verifiable rewards. This shift directly targets the semantic gap between superficially compilable code and physically executable quantum programs. In addition, we identify key research opportunities-such as standardized semantic metrics and integration with quantum error correction-aimed at fostering a more reproducible, verifiable, and hardware-grounded ecosystem for automated quantum software development.
Large Language Models (LLMs) such as GPT and LLaMA have transformed artificial intelligence, but their rapid growth has brought major challenges in computation, energy use, and scalability. Quantum computing (QC) offers a fundamentally different way to process information, with the potential to accelerate key operations in training, inference, optimization, and representation learning. This survey provides a structured and comprehensive review of how QC can support the future development of LLMs. It examines quantum algorithms, hybrid quantum-classical methods, quantum neural networks, quantum embeddings, and security applications. It also evaluates their feasibility in both the current noisy intermediate-scale quantum (NISQ) era and the future fault-tolerant era. The survey highlights current progress, identifies major technical barriers, and outlines practical research directions needed to build scalable, efficient, and secure quantum-enhanced language models.