Agentic AI for Multi-Stage Physics Experiments at a Large-Scale User Facility Particle Accelerator
This enables safe integration of agentic AI into accelerator experiments and other large-scale scientific infrastructures, potentially transforming routine operations.
The researchers developed the first language-model-driven agentic AI system to autonomously execute multi-stage physics experiments at a particle accelerator, reducing preparation time by two orders of magnitude compared to manual scripting while maintaining safety constraints.
We present the first language-model-driven agentic artificial intelligence (AI) system to autonomously execute multi-stage physics experiments on a production synchrotron light source. Implemented at the Advanced Light Source particle accelerator, the system translates natural language user prompts into structured execution plans that combine archive data retrieval, control-system channel resolution, automated script generation, controlled machine interaction, and analysis. In a representative machine physics task, we show that preparation time was reduced by two orders of magnitude relative to manual scripting even for a system expert, while operator-standard safety constraints were strictly upheld. Core architectural features, plan-first orchestration, bounded tool access, and dynamic capability selection, enable transparent, auditable execution with fully reproducible artifacts. These results establish a blueprint for the safe integration of agentic AI into accelerator experiments and demanding machine physics studies, as well as routine operations, with direct portability across accelerators worldwide and, more broadly, to other large-scale scientific infrastructures.