Large language model framework automates lattice qcd parton distribution analysis
LaMET-Agent: An Agent Framework for Large-Momentum Effective Theory Analysis
Artificial Intelligence
Summary
Understanding the inner structure of particles like protons involves complex calculations using lattice quantum chromodynamics (QCD). These calculations are typically tedious and require expert knowledge. The authors created lamet-agent, a software framework that uses large language models to automate and organize these calculations into a clear, repeatable pipeline. They tested it on several particle analyses and found it produces results matching previous studies. This tool aims to reduce manual effort and make these advanced physics analyses more accessible.
What this means in practice
- •For computational physics software developers: Integrate automated analysis workflows for lattice QCD parton distributions into scientific software tools to improve reproducibility and reduce expert intervention.
- •For high-energy physics data analysts: Employ the framework to streamline multi-stage lattice QCD calculations for parton physics, enhancing efficiency and consistency in research pipelines.
Authors
Jinchen He, Xiangyu Jiang, Fei Yao, Dian-Jun Zhao
Abstract
Large-momentum effective theory (LaMET) provides a first-principles framework for computing the $x$ dependence of light-cone parton distributions from lattice QCD. Over the past decade, theoretical and numerical advances have established a mature multi-stage workflow for systematic calculation of parton physics, although its implementation still requires expert judgment and substantial repeated effort. We present lamet-agent, an open-source large language model (LLM) agent framework that organizes this workflow into an executable, reproducible, and inspectable analysis pipeline. The present release supports collinear quark distributions and implements correlator analysis, renormalization, Fourier transformation, perturbative matching, continuum, physical pion mass and infinite-momentum extrapolations, and automated result review. We validate it on four end-to-end analyses: pion parton distribution functions in the gauge-invariant and Coulomb-gauge formulations, and pion and kaon distribution amplitudes, obtaining results consistent with the published calculations. Extensions to transverse-momentum-dependent distributions, generalized transverse-momentum-dependent distributions, and gluonic distribution functions are planned for subsequent releases.