Reza Salkhordeh

Trapped-ion quantum computers rely on shuttling compilers, which cast an input algorithm into a sequence of ion-qubit movements within a given architecture. We present the first study in which a single frontier large language model (LLM), Claude Opus 4.7, generates and iteratively refines the full Python code of shuttling compilers from written specifications. We start with a compiler for (i) a linear segmented trap, extend it to (ii) a trap with junctions, and finally achieve efficient compilation for (iii) a broad class of connected trap graphs. The compilers for the more general cases are seeded with code from the previous ones. We benchmark the LLM-generated compilers against state-of-the-art hand-crafted ones using a common suite of quantum circuits. The number of shuttling timesteps is reduced by up to 76% for (i) and up to 39% for (ii). For the broad case (iii) of freely connected architectures, we find large variations in the required number of shuttling timesteps, depending on the connectivity. A densely connected, junction-rich architecture yields an order-of-magnitude reduction in shuttling timesteps compared to a corridor-like one. Repeating the complete generation and evaluation with a second frontier LLM, Claude Fable 5, reproduces these findings, with the Fable 5 compilers surpassing the hand-crafted ones more often on the largest circuits. Our results show that an unmodified frontier LLM can produce working, correct, and competitive shuttling compilers without additional manual algorithmic engineering, thus reducing the development time for new architectures from several months to a few days.

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).