mlsanityData to 14 Oct 2026

Quantum Verifiable Rewards for Post-Training Qiskit Code Assistant

arXiv 2508.20907 ↗First posted 28 Aug 2025quant-ph cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Qiskit is an open-source quantum computing framework that allows users to design, simulate, and run quantum circuits on real quantum hardware. We explore post-training techniques for LLMs to assist in writing Qiskit code. We introduce quantum verification as an effective method for ensuring code quality and executability on quantum hardware. To support this, we developed a synthetic data pipeline that generates quantum problem-unit test pairs and used it to create preference data for aligning LLMs with DPO. Additionally, we trained models using GRPO, leveraging quantum-verifiable rewards provided by the quantum hardware. Our best-performing model, combining DPO and GRPO, surpasses the strongest open-source baselines on the challenging Qiskit-HumanEval-hard benchmark.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 27 of its 40 references that are in the map. First posted on arXiv 28 Aug 2025.

Builds on

27 of 40 references.

References · 27

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  6. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  7. 2017Deep reinforcement learning from human preferencescited by 3,912
  8. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  9. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
  10. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,218
  11. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,386
  12. 2024Qwen2.5-Coder Technical Reportcited by 1,203
15 more
  1. 2023CodeT5+: Open Code Large Language Models for Code Understanding and Generationcited by 333
  2. 2024Arcee's MergeKit: A Toolkit for Merging Large Language Modelscited by 194
  3. 2022Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deploymentcited by 108
  4. 2024Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Modelscited by 73
  5. 2025Training a Scientific Reasoning Model for Chemistrycited by 56
  6. 2024Qiskit HumanEval: An Evaluation Benchmark For Quantum Code Generative Modelscited by 30
  7. 2024Qiskit Code Assistant: Training LLMs for generating Quantum Computing Codecited by 25
  8. 2025Agent-Q: Fine-Tuning Large Language Models for Quantum Circuit Generation and Optimizationcited by 17
  9. 2025Enhancing LLM-based Quantum Code Generation with Multi-Agent Optimization and Quantum Error Correctioncited by 11
  10. 2025QHackBench: Benchmarking Large Language Models for Quantum Code Generation Using PennyLane Hackathon Challengescited by 8
  11. 2025PennyCoder: Efficient Domain-Specific LLMs for PennyLane-Based Quantum Code Generationcited by 6
  12. 2025Q-Fusion: Diffusing Quantum Circuitscited by 4
  13. 2025Taxonomy of migration scenarios for Qiskit refactoring using LLMscited by 2
  14. 2025QSpark: Towards Reliable Qiskit Code Generationcited by 2
  15. 2025Automatic Qiskit Code Refactoring Using Large Language Modelscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 5.

6 papers.

  1. 2025QUASAR: Quantum Assembly Code Generation Using Tool-Augmented LLMs via Agentic RLcited by 11
  2. 2026QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generationcited by 2
  3. 2026Qiskit QuantumKatas: Adapting Microsoft's Quantum Computing exercises for LLM evaluationcited by 2
  4. 2026Aligning Quantum Operators with Large Language Modelscited by 1
  5. 2026Generative AI for Quantum Circuits and Quantum Code: A Technical Review and Taxonomycited by 0
  6. 2026Fine-Tuning Large Language Models for Quantum Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024KetGPT - Dataset Augmentation of Quantum Circuits using Transformers
  2. 2026Beyond Rules: LLM-Powered Linting for Quantum Programs ↗
  3. 2026PennySynth: RAG-Driven Data Synthesis for Automated Quantum Code Generation
  4. 2026Quantum-Audit: Evaluating the Reasoning Limits of LLMs on Quantum Computing
  5. 2025Model-Driven Quantum Code Generation Using Large Language Models and Retrieval-Augmented Generation
  6. 2025DeQompile: quantum circuit decompilation using genetic programming for explainable quantum architecture search
  7. 2025Platform-Agnostic Modular Architecture for Quantum Benchmarking
  8. 2025QAgent: An LLM-based Multi-Agent System for Autonomous OpenQASM programming