发表机构
NVIDIA; Lawrence Berkeley National Laboratory; Quantum Computing Data; Cascade Quantum（英伟达; 劳伦斯伯克利国家实验室; 量子计算数据; Cascade量子）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文以QED-C基准测试从Qiskit到CUDA-Q的自主迁移为案例，测试Opus、GPT、Gemini模型的迁移能力，发现多智能体集成策略可缓解量子软件迁移挑战，相关技能能大幅降低模型交互轮次和令牌使用量。
AI 中文摘要
量子编程所需的概念和直觉与传统编程语言存在显著差异。多个量子编程框架通过不同的抽象和执行模型满足这些需求，在可编程性、可移植性和性能方面形成了权衡。由于大型语言模型可用的训练数据中量子软件较少，自主编码智能体在处理这些框架时可能面临额外挑战。本文开展了一项案例研究，将QED-C面向应用的基准测试从Qiskit自主迁移到CUDA-Q。Opus、GPT和Gemini模型各自承担了13个基准测试方法的迁移任务，这些方法涵盖基础算法、振幅估计、蒙特卡洛方法、变分优化、线性系统求解和因式分解。在所有案例中，模型仅需少量直接编码帮助就能生成令人满意的迁移代码，且所需时间与人类工程师相比大幅缩短。然而，在遇到实现挑战时，所有智能体都采用了捷径，需要多次提示才能引导至合适的编码方向。对生成的实现的评估显示，没有任何单一模型能在所有基准测试中始终生成最佳迁移代码，这表明多智能体集成策略可缓解与量子软件相关的挑战。该工作实现了QED-C基准测试中公开可用的近乎完整的CUDA-Q支持，以及旨在提升智能体实现CUDA-Q应用性能的模型生成技能。在对未见过的基准测试进行测试时，这些技能将所需的模型交互轮次减少了多达85%，令牌使用量减少了多达96%。最后，本文从该案例研究中提炼出经验教训。
英文摘要
Quantum programming requires concepts and intuition that differ substantially from those used in traditional programming languages. Multiple quantum programming frameworks address these requirements through different abstractions and execution models, creating tradeoffs in programmability, portability, and performance. Because quantum software is less prevalent in the training data available to large language models, autonomous coding agents might be expected to face additional challenges when working with these frameworks. We present a case study in autonomous migration of the QED-C Application-Oriented Benchmarks from Qiskit to CUDA-Q. Opus, GPT, and Gemini models were each tasked with porting thirteen benchmark methods spanning foundational algorithms, amplitude estimation, Monte Carlo methods, variational optimization, linear-system solving, and factoring. In all cases, the models were able to generate satisfactory ports with little direct coding help and there was a drastic reduction in the time required compared to a human engineer. However, in all cases, the agents resorted to shortcuts when implementation challenges surfaced and multiple prompts were required to force appropriate coding directions. Assessment of the generated implementations showed that no single model consistently produced the best port across all benchmarks, indicating that multi-agent ensemble strategies could mitigate challenges associated with quantum software. The effort resulted in publicly available, near-complete CUDA-Q support in the QED-C benchmarks along with model-generated skills designed to improve agent performance when implementing CUDA-Q applications. When tested on an unseen benchmark, these skills reduced the required model turns by up to 85% and token usage by up to 96%. We conclude by distilling lessons from the case study.
Comments13 Pages, 1 Figure, 10 Tables
