CoLLM: AI engineering toolbox for end-to-end deep learning in collider analyses

TL;DR

CoLLM is an AI toolkit that leverages large language models to generate analysis code, automate deep learning workflows, and provide an interactive interface, simplifying collider analyses for users with limited programming expertise.

Contribution

It introduces a comprehensive AI-powered toolbox that automates code generation and analysis workflows for collider physics, reducing technical barriers and enhancing accessibility.

Findings

Successfully generates physically consistent analysis code

Automates deep learning analysis steps

Provides an interactive graphical user interface

Abstract

Recent improvements in large language models have opened new opportunities for accelerating and automating scientific workflows. In parallel, modern collider analyses are becoming increasingly complex and demand substantial programming and deep learning expertise. \coll alleviates this workload by using pretrained large language models to generate physically consistent analysis code for event selection. Additionally, it automates subsequent deep learning analyses. To further reduce reliance on programming or deep learning experience, \coll provides a graphical user interface that allows users to perform end-to-end analyses through an interactive interface. The main motivation behind \coll is to lower the coding burden and simplify the technical complexity of collider analyses, which increasingly depend on sophisticated event selections and advanced deep learning methods.