Controlling quantum hardware requires choosing and revising experimental strategies as nonlinear response, coupling, and drift limit calibration. We experimentally investigate a general-purpose large language model (LLM) as a human-in-the-loop strategy layer for a neutral-atom tweezer platform. Through step-by-step interaction with experimental feedback, the LLM guides a transition from multiplicative row--column correction to a drift-corrected local response-matrix method when separable feedback stalls. Deterministic software performs image analysis and numerical updates, while an experimentalist verifies and authorizes each waveform. For a $10\times10$ crossed-acousto-optic-deflector array, this workflow reduces the Gaussian-peak coefficient of variation from $20.30\%$ to $1.57\%$ in 30 candidate-update rounds. The experiment demonstrates feedback-informed strategy selection on a physical quantum-control subsystem, rather than direct generation of control parameters alone. These results highlight the potential of LLMs to guide control optimization across diverse quantum platforms by adaptively formulating and refining experimental strategies.
Controlling quantum hardware requires choosing and revising experimental strategies as nonlinear response, coupling, and drift limit calibration. We experimentally investigate a general-purpose large language model (LLM) as a human-in-the-loop strategy layer for a neutral-atom tweezer platform. Through step-by-step interaction with experimental feedback, the LLM guides a transition from multiplicative row--column correction to a drift-corrected local response-matrix method when separable feedback stalls. Deterministic software performs image analysis and numerical updates, while an experimentalist verifies and authorizes each waveform. For a 10×10 crossed-acousto-optic-deflector array, this workflow reduces the Gaussian-peak coefficient of variation from 20.30% to 1.57% in 30 candidate-update rounds. The experiment demonstrates feedback-informed strategy selection on a physical quantum-control subsystem, rather than direct generation of control parameters alone. These results highlight the potential of LLMs to guide control optimization across diverse quantum platforms by adaptively formulating and refining experimental strategies.
Quantum optimal control (QOC) underpins adiabatic quantum computation, quantum annealing, and quantum state engineering, yet practical deployment is fundamentally bottlenecked by strict hardware constraints and substantial expert effort required to design protocols for each problem instance. To overcome this, we introduce QOC-Workbench, an auditable, large language model (LLM)-driven workflow that acts as an automated quantum co-scientist for cross-paradigm protocol design. Going beyond traditional numerical optimizers that merely tune parameters within a fixed formula, the LLM autonomously parses physics literature, proposes structural hypotheses, and writes code to validate them by direct simulation. This workflow supports cross-paradigm design by accumulating control motifs across tasks. We demonstrate this approach across three distinct settings: Case 1, Rydberg-atom maximum-independent-set arrays; Case 2, interacting XXZ spin chains; and Case 3, random transverse-field Ising models. In Cases 1 and 2, the workflow autonomously discovers hardware-compliant auxiliary controls, target catalysts, and schedule deformations that outperform literature baselines. In Case 3, it addresses the computational bottleneck of variational counterdiabatic driving by escalating from per-instance optimization to an amortized graph-neural-network generator, successfully transferring learned coefficient paths to larger unseen systems. By actively bridging the gap between theoretical algorithms and experimental restrictions across distinct control paradigms and Hamiltonian families, QOC-Workbench establishes a continuously evolving, cross-paradigm methodology for autonomous quantum control.
Quantum control is essential for quantum information science and technology, yet designing high-fidelity control protocols remains challenging due to complex optimization landscapes, hardware noise, and long pulse sequences. Existing numerical solvers often require problem-specific engineering and produce opaque control amplitudes, while naive large language models (LLMs) lack the physical consistency and long-horizon precision for reliable quantum control synthesis. Here we introduce VF-QCTRL, a physics-informed large language model framework for general quantum control that combines symbolic reasoning with optimization to propose analytic control ansätze and coherently refine their parameters through feedback. To systematically evaluate LLM-driven quantum control, we develop QCTRL-BENCH, a benchmark spanning sixteen tasks across single- and multi-qubit systems, closed and open quantum dynamics, noiseless and noisy settings, and both analytic and numerical protocols. Across the benchmark, VF-QCTRL demonstrates strong universality, accuracy, efficiency, and interpretability: it applies to generic quantum control systems without task-specific training, achieves performance competitive with or exceeding state-of-the-art conventional solvers in both noiseless and noisy regimes with query efficiency, exhibits favorable inference-time scaling and pulse resolution scaling, and derives physically interpretable analytical protocols directly from prompts. Our results establish physics-informed LLM-based quantum control as a promising paradigm for accurate, efficient, interpretable, and training-free quantum control protocol design across a broad range of quantum systems.
Large-language-model (LLM) agents can write and run experimental control code. This allows laboratory work to be conducted autonomously. However, this autonomy raises a safety problem that prior work has not addressed. Unchecked code can damage the apparatus, and there is no formal, per-operation boundary between human authorization/supervision, and agent decisions. We present a control system that places an LLM agent in the loop of a trapped-ion experiment while enforcing such a boundary. The agent controls the existing Advanced Real-Time Infrastructure for Quantum physics (ARTIQ) stack through tools provided by a Model Context Protocol (MCP) server. No tool call reaches the hardware unless it carries an authorization token bound to its exact contents. Tokens are issued in one of two ways: automatically, by running the agent's proposed script in an isolated hardware simulation (dax.sim) and checking every operation against preset per-device bounds, or manually by a human operator for sensitive actions. Within this boundary the agent develops its own experiments, rather than only calling pre-built routines. We deploy the system on a co-trapped 40Ca+/40CaOH+ crystal, where the agent autonomously builds a full calibration stack and, with targeted operator guidance, closes a cross-instrument magnetic-field-stabilization loop. On a separate, independent 171Yb+ platform, we confirm interface-level portability. We systematically test token-authorization mechanism with adversarial scripts that attempt to bypass it, mapping the precise boundary of its protection and prioritizing where to strengthen it next. Analyzing where the agent still requires human guidance, we find that its limits lie in metacognitive control, namely recognizing when a problem must be re-framed, rather than in domain knowledge.
The design of high performing quantum circuits remains largely dependent on human expertise. We introduce an autonomous agentic framework that employs large language models (LLMs) to conduct iterative quantum circuit designs under explicit design constraints. Our system integrates seven components: Exploration, Generation, Discussion, Validation, Storage, Evaluation, and Review. These components form a closed-loop workflow that combines web-based knowledge acquisition, literature-grounded critique, executable code generation, and experimental feedback. We evaluate the framework on two tasks: quantum feature map construction for quantum machine learning and ansatz generation for variational quantum eigensolver applications in quantum chemistry. In image classification benchmarks, the best generated feature map outperforms representative quantum feature maps and, when scaled to larger qubit counts, surpasses the classical radial basis function kernel. In molecular ground state estimation across seven molecules, the generated ansatz attains competitive accuracy with widely used chemically inspired and hardware-efficient constructions while satisfying the imposed scaling constraints. These results establish LLM driven agentic system as a viable paradigm for automated quantum circuit design and illustrate how AI systems can participate in iterative scientific optimization workflows across scientific domains.
Reconfigurable arrays of neutral atoms are a leading platform for quantum computing, quantum simulation, and quantum metrology. The most common method for atom reconfiguration using optical tweezers relies on frequency chirping of acousto-optic deflectors (AODs). However, chirp-induced acoustic lensing limits the speed of atom transport by deformation of the tweezer profile and warping of the tweezer trajectory. We use a three-dimensional acousto-optic deflector lens (3D-AODL) to mitigate both effects, a design predicted to halve current state-of-the-art long-range transport times. Additionally, we introduce fading-Shepard waveforms that bypass the finite AOD bandwidth and thus enable sustained axial displacement. We demonstrate unrestricted 3D motion within a cuboid volume of at least 200 μm × 200 μm × 136 μm, with tweezer velocities exceeding 4.2 m/s. The ability to move optical tweezers along arbitrary trajectories in 3D should enable rapid in-plane and out-of-plane rearrangement of atoms in 2D or 3D tweezer arrays and optical lattices, as well as omnidirectional trajectories and dynamical engineering of optical potentials. This technology has the potential to advance quantum control and atom manipulation in current atom-array quantum computers, boosting clock rates and enabling rapid sorting in geometries scalable to millions of qubits.
Superconducting circuits have demonstrated significant potential in quantum information processing and quantum sensing. Implementing novel control and measurement sequences for superconducting qubits is often a complex and time-consuming process, requiring extensive expertise in both the underlying physics and the specific hardware and software. In this work, we introduce a framework that leverages a large language model (LLM) to automate qubit control and measurement. Specifically, our framework conducts experiments by generating and invoking schema-less tools on demand via a knowledge base on instrumental usage and experimental procedures. We showcase this framework with two experiments: an autonomous resonator characterization and a direct reproduction of a quantum non-demolition (QND) characterization of a superconducting qubit from literature. This framework enables rapid deployment of standard control-and-measurement protocols and facilitates implementation of novel experimental procedures, offering a more flexible and user-friendly paradigm for controlling complex quantum hardware.