ArXiv ID: 2603.20179
Summary: Large language model-based AI agents are now able to autonomously execute substantial portions of a high energy physics (HEP) analysis pipeline with minimal expert-curated input. Using Claude Code, authors find it succeeds in automating all stages of a typical analysis: event selection, background estimation, uncertainty quantification, statistical inference, and paper drafting. The framework "Just Furnish Context" (JFC) integrates autonomous analysis agents with literature-based knowledge retrieval and multi-agent review.