Trapped-ion quantum computers based on segmented traps rely on shuttling operations to establish long-range connectivity between sub-registers. Qubit routing dynamically reconfigures qubit positions so that all qubits involved in a gate operation are co-located within the same segment, a task whose complexity increases with system size. To address this challenge, we propose a layout-independent compilation strategy based on large language models (LLMs). Specifically, we fine-tune pretrained LLMs to generate the required shuttling operations. We evaluate this approach on linear and branched one-dimensional architectures using quantum circuits of up to $16$ qubits. Our results show that the fine-tuned LLMs generate valid shuttling schedules and, in some cases, outperform previous shuttling compilers by requiring approximately $15\,\%$ less shuttle overhead. However, results degrade as the algorithms increase in width and depth. In future, we plan to improve LLM-based shuttle compilation by enhancing our training pipeline using Direct Preference Optimization (DPO) and Gradient Regularized Policy Optimization (GRPO).

翻译：基于分段阱的囚禁离子量子计算机依赖穿梭操作在子寄存器间建立长程连接。量子比特路由通过动态重配置比特位置，使得参与门操作的所有量子比特共处于同一阱段，该任务的复杂度随系统规模增加而提升。为应对这一挑战，我们提出一种基于大语言模型（LLMs）的布局无关编译策略。具体而言，我们通过微调预训练LLMs来生成所需的穿梭操作。我们在包含最多$16$个量子比特的线型和分支型一维架构上评估该方法。结果表明，经微调的LLMs能生成有效的穿梭调度方案，且在部分案例中较先前穿梭编译器减少约$15\,\%$的穿梭开销。然而，当算法宽度与深度增加时，性能会出现下降。未来我们计划通过采用直接偏好优化（DPO）和梯度正则化策略优化（GRPO）改进训练流程，以提升基于LLM的穿梭编译性能。