Proposal of an AI-Based Support Assistant for the ALICE-FIT Detector Setup at CERN

TL;DR

This paper introduces an AI-based support assistant leveraging LLMs and RAG to aid CERN ALICE-FIT detector operators in diagnosing and resolving operational issues efficiently with context-aware suggestions.

Contribution

It presents a novel AI assistant system that combines LLMs with retrieval techniques to improve operational support for complex detector systems.

Findings

Enhanced diagnostic support for ALICE-FIT operators

Effective integration of LLMs with retrieval-augmented generation

Potential to reduce downtime and improve decision-making

Abstract

We propose an AI-based assistant designed to support the ALICE Fast Interaction Trigger (FIT) detector operators at CERN. The assistant helps diagnose and resolve operational issues in the Detector Control System (DCS), where decisions must often be made quickly and with incomplete information. By combining Large Language Models (LLMs) with a controlled Retrieval-Augmented Generation (RAG) pipeline, the system can generate context-aware suggestions based on verified ALICE-FIT documentation and problems that have appeared in the past.