Dr.Sai: An agentic AI for real-world physics analysis at BESIII

TL;DR

Dr.Sai is an AI system using large language models to autonomously perform complex physics data analysis at BESIII, streamlining workflows and enabling large-scale systematic scans.

Contribution

It introduces Dr.Sai, a novel multi-agent LLM-powered system that translates natural language into physics workflows, validated on real BESIII data without manual coding.

Findings

Successfully re-measured ten J/psi decay branching fractions

Matched results with established benchmarks

Operated effectively within the BESIII computing environment

Abstract

High Energy Physics (HEP) experiments like BESIII produce petabyte-scale data. Extracting physics results requires complex workflows (simulation, reconstruction, statistical analysis, etc.) that traditionally take experts months or years. Current manual methods are labor-intensive, prone to bias, and limit large-scale systematic scans. As data grows, this paradigm slows discovery. Large Language Models (LLMs) offer a solution. Their natural language understanding and code generation capabilities allow them to interpret scientific tasks and integrate with HEP tools (e.g., ROOT, BOSS) to act as an "AI partner" for autonomous analysis. We present Dr.Sai, an LLM-powered multi-agent system that translates natural language into rigorous physics workflows. As validation, Dr.Sai performed large-scale re-measurements of ten J/psi decay branching fractions - without manual coding. It successfully navigated the real BESIII computing environment and produced results matching established benchmarks. The article details Dr.Sai's architecture, the validation results, and performance evaluation. This work provides a blueprint for autonomous discovery, with relevance to other data-intensive fields like astronomy and genomics.