Large Language Models for Combinatorial Optimization: A Systematic Review

TL;DR

This systematic review analyzes how Large Language Models are applied to combinatorial optimization, categorizing existing research, datasets, and applications to guide future developments in the field.

Contribution

It provides a comprehensive classification and overview of 103 studies on LLMs in combinatorial optimization, highlighting current trends and future research directions.

Findings

Classified studies into semantic categories and topics

Identified key datasets and evaluation benchmarks

Outlined future research directions in LLM applications for CO

Abstract

This systematic review explores the application of Large Language Models (LLMs) in Combinatorial Optimization (CO). We report our findings using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. We conduct a literature search via Scopus and Google Scholar, examining over 2,000 publications. We assess publications against four inclusion and four exclusion criteria related to their language, research focus, publication year, and type. Eventually, we select 103 studies. We classify these studies into semantic categories and topics to provide a comprehensive overview of the field, including the tasks performed by LLMs, the architectures of LLMs, the existing datasets specifically designed for evaluating LLMs in CO, and the field of application. Finally, we identify future directions for leveraging LLMs in this field.