arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.03466quant-phstat.ML

通过大语言模型的测试时学习生成量子电路

Quantum Circuit Generation via test-time learning with large language models

Università degli Studi di Palermo(巴勒莫大学)

Adriano Macarone-Palmieri, Rosario Lo Franco

AI总结:

研究通过大语言模型进行量子电路生成,提出记忆增强测试时优化框架,结合情景记忆、分数差反馈和重新采样改进搜索。在量子电路合成任务中评估,结果显示该框架显著提高样本效率,为测试时优化提供挑战基准。

摘要:

将大语言模型(LLMs)用作黑箱科学设计问题的优化器,需要在昂贵评估且无训练数据的情况下进行高效测试时优化。我们提出了一个记忆增强测试时优化框架,结合高分候选者的情景记忆、分数差反馈和从最佳样本重新开始采样来改进迭代搜索。我们在量子电路合成中评估该方法,目标是在指数级昂贵的黑箱预言机下最大化迈耶 - 瓦拉赫(MW)全局纠缠度量。在20量子比特电路上,该框架在无反馈时达到\(Q(\psi)=0.99\)。在更具挑战性的25量子比特任务中,反馈和重新开始机制使多次运行能在45次预言机调用内达到\(Q(\psi)=1.0\),而预算匹配的随机爬山基线在\(Q(\psi)\approx0.29\)以下停滞。这些结果表明记忆和评估器反馈显著提高了基于LLM的黑箱优化的样本效率,并将量子电路合成确立为测试时优化的具有挑战性的基准。

英文摘要:

Deploying large language models (LLMs) as optimizers for black-box scientific design problems requires efficient test-time refinement under expensive evaluations and without training data. We propose a \emph{memory-augmented test-time optimization} framework that combines episodic memory of high-scoring candidates, score-difference feedback, and restart-from-best sampling to improve iterative search. We evaluate the approach on quantum circuit synthesis, where the objective is to maximize the Meyer--Wallach (MW) global entanglement measure under an exponentially expensive black-box oracle. On 20-qubit circuits, the framework achieves $Q(ψ)=0.99$ without feedback. On the more challenging 25-qubit task, feedback and restart mechanisms enable multiple runs to reach $Q(ψ)=1.0$ within 45 oracle calls, while a budget-matched random hill-climbing baseline stalls below $Q(ψ)\approx0.29$. These results demonstrate that memory and evaluator feedback substantially improve the sample efficiency of LLM-based black-box optimization and establish quantum circuit synthesis as a challenging benchmark for test-time optimization.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑