A Comprehensive Evaluation of Contemporary Machine-Learning-Based Solvers for CO

Shengyu Feng, Weiwei Sun, Shanda Li, Ameet Talwalkar, Yiming Yang

Keywords: Combinatorial Optimization, Graph Neural Networks, Language Language Model Agents

TL;DR: We introduce challenging real-world instances for 8 combinatorial optimization problems, evaluating 16 recent machine learning-based solvers.

Abstract: Machine learning (ML) has demonstrated considerable potential in supporting model design and optimization for combinatorial optimization (CO) problems. However, much of the progress to date has been evaluated on small-scale, synthetic datasets, raising concerns about the practical effectiveness of ML-based solvers in real-world, large-scale CO scenarios. Additionally, many existing CO benchmarks lack sufficient training data, limiting their utility for evaluating data-driven approaches. To address these limitations, we introduce **FrontierCO**, a comprehensive benchmark that covers eight canonical CO problem types and evaluates 16 representative ML-based solvers, including graph neural networks and large language model (LLM) agents. FrontierCO features challenging instances drawn from industrial applications and frontier CO research, offering both realistic problem difficulty and abundant training data. Our empirical results provide critical insights into the strengths and limitations of current ML methods, helping to guide more robust and practically relevant advances at the intersection of ML and CO.

Submission Number: 51