AI Agents Can Already Autonomously Perform Experimental High Energy Physics
Large language model-based AI agents can execute substantial portions of a high energy physics analysis pipeline with minimal expert-curated input, achieving all stages of a typical analysis. This breakthrough has significant implications for the field of physics and demonstrates the growing capabilities of AI agents. The use of AI in physics research could lead to faster discovery and more efficient experimentation. With access to a HEP dataset, an execution framework, and a corpus of prior experimental literature, Claude Code succeeds in automating event selection, background estimation, uncertainty quantification, and statistical analysis.