Discovering Models for Experimental Quantum Systems with Agentic AI
Organizations: Edward L. Ginzton Laboratory, Stanford University, Stanford, CA, USA. · Max Planck Institute of Quantum Optics, Garching, Germany. · Departamento de Física Teórica de la Materia Condensada, Universidad Autónoma de Madrid, E-28049 Madrid, Spain. · Condensed Matter Physics Center (IFIMAC), Universidad Autónoma de Madrid, E-28049 Madrid, Spain. ·
Abstract
A central obstacle in realizing color center cavity-QED-based quantum technologies is inhomogeneity, or disorder, among individual emitters. As the number of emitters increases, so does the complexity of the experimental data, making it difficult to quantify the present physical mechanisms of disorder. Here we introduce an artificial intelligence-driven model discovery framework in which a large language model (LLM)-based agent, equipped with tools and a structured workflow, proposes candidate Hamiltonian and Lindbladian models, generates computational tools, and quantitatively evaluates competing physical hypotheses. We apply the workflow to three previously published experimental cavity-QED datasets collected from color centers in diamond and silicon carbide. Across the experiments, the agent successfully identifies physical models for the system and characterizes the disorder. In assessing reproducibility, we find that run-to-run variability is concentrated primarily in the research plan generation step, while the computational analysis itself is substantially more consistent. Our results suggest that structured LLM agent workflows can support model discovery from quantum optical experimental data while simultaneously allowing for human expert supervision and collaboration.
Figures & tables
| Model / Effect | Description | # Parameters |
| SnV experiment | ||
| M1 | Single emitter, with a C transition (frequency , coupling ), D transition (detuning ), and off-resonant spontaneous emission ( ). | 4 |
| M2 | Two independent emitters, with count amplitude ratios & and shared . | 8 |
| M2c | Two collective emitters (collective decay and coherent exchange ). | 10 |
| M3 | Three independent emitters. | 12 |
| M4 | Four independent emitters. | 16 |
Quantum System Identification
Quantum system identification infers a quantum device’s dynamics, parameters, and environmental noise from experimental measurements.
See all 17 papers