QSpark: Towards Reliable Qiskit Code Generation
Not on the map. Why?
Abstract (arXiv)
Quantum circuits must be error-resilient, yet LLMs like Granite-20B-Code and StarCoder often output flawed Qiskit code. We fine-tuned the Qwen2.5-Coder-32B model with two RL methods, Group Relative Policy Optimization (GRPO) and Odds-Ratio Preference Optimization (ORPO), using a richly annotated synthetic dataset. On the Qiskit HumanEval benchmark, ORPO reaches 56.29% Pass@1 (≈+10 pp over Granite-8B-QK) and GRPO hits 49%, both beating all general-purpose baselines; on the original HumanEval they score 65.90% and 63.00%. GRPO performs well on basic tasks (44/78) and excels on intermediate ones (41/68), but neither GRPO nor ORPO solves any of the five advanced tasks, highlighting clear gains yet room for progress in AI-assisted quantum programming.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 12 of its 25 references that are in the map. First posted on arXiv 16 Jul 2025.
Builds on
12 of 25 references.
References · 12
- 2021Evaluating Large Language Models Trained on Codecited by 8,320
- 2023StarCoder: may the source be with you!cited by 799
- 2024CodeGemma: Open Code Models Based on Gemmacited by 150
- 2024Granite Code Models: A Family of Open Foundation Models for Code Intelligencecited by 117
- 2020Queueing Network Controls via Deep Reinforcement Learningcited by 41
- 2024Qiskit HumanEval: An Evaluation Benchmark For Quantum Code Generative Modelscited by 30
- 2024Qiskit Code Assistant: Training LLMs for generating Quantum Computing Codecited by 25
- 2019Quantum Computing based Hybrid Solution Strategies for Large-scale Discrete-Continuous Optimization Problemscited by 11
- 2018Quantum Codes from Neural Networkscited by 6
- 2024Quantum Software Engineering: Roadmap and Challenges Aheadcited by 6
- 2024C4Q: A Chatbot for Quantumcited by 3
- 2024Towards View-based Development of Quantum Softwarecited by 1
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2026Generative AI for Quantum Circuits and Quantum Code: A Technical Review and Taxonomy
- 2025QHackBench: Benchmarking Large Language Models for Quantum Code Generation Using PennyLane Hackathon Challenges
- 2026Qiskit QuantumKatas: Adapting Microsoft's Quantum Computing exercises for LLM evaluation
- 2026PennySynth: RAG-Driven Data Synthesis for Automated Quantum Code Generation
- 2025Enhancing LLM-based Quantum Code Generation with Multi-Agent Optimization and Quantum Error Correction
- 2026Revisiting Quantum Code Generation: Where Should Domain Knowledge Live?
- 2025Model-Driven Quantum Code Generation Using Large Language Models and Retrieval-Augmented Generation
- 2025PennyCoder: Efficient Domain-Specific LLMs for PennyLane-Based Quantum Code Generation