# QSpark: Towards Reliable Qiskit Code Generation

arXiv: https://arxiv.org/abs/2507.12642 · HTML: https://mlsanity.com/paper/2507.12642/

## 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 (most cited first, 12 of 12)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [CodeGemma: Open Code Models Based on Gemma](https://mlsanity.com/paper/2406.11409/) (2024)
- [Granite Code Models: A Family of Open Foundation Models for Code Intelligence](https://mlsanity.com/paper/2405.04324/) (2024)
- [Queueing Network Controls via Deep Reinforcement Learning](https://mlsanity.com/paper/2008.01644/) (2020)
- [Qiskit HumanEval: An Evaluation Benchmark For Quantum Code Generative Models](https://mlsanity.com/paper/2406.14712/) (2024)
- [Qiskit Code Assistant: Training LLMs for generating Quantum Computing Code](https://mlsanity.com/paper/2405.19495/) (2024)
- [Quantum Computing based Hybrid Solution Strategies for Large-scale Discrete-Continuous Optimization Problems](https://mlsanity.com/paper/1910.13045/) (2019)
- [Quantum Codes from Neural Networks](https://mlsanity.com/paper/1806.08781/) (2018)
- [Quantum Software Engineering: Roadmap and Challenges Ahead](https://mlsanity.com/paper/2404.06825/) (2024)
- [C4Q: A Chatbot for Quantum](https://mlsanity.com/paper/2402.01738/) (2024)
- [Towards View-based Development of Quantum Software](https://mlsanity.com/paper/2406.18363/) (2024)

## Built on by (most cited first, 2 of 2)

- [Quantum Verifiable Rewards for Post-Training Qiskit Code Assistant](https://mlsanity.com/paper/2508.20907/) (2025)
- [When AI meets quantum information: A comprehensive review](https://mlsanity.com/paper/2607.00365/) (2026)

## 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.