MMODELYST
Papers/Towards Generalization-Oriented Models for Vehicle Routing Problems with Mixture-of-Experts
PAP

Towards Generalization-Oriented Models for Vehicle Routing Problems with Mixture-of-Experts

May 26, 2026

arXiv
Abstract

In recent years, Deep Reinforcement Learning (DRL) has achieved substantial progress on Vehicle Routing Problems (VRPs). However, existing DRL-based methods are typically trained on instances generated from a uniform distribution, which limits their performance under real-world distribution shifts. In this paper, we aim to develop a generalization-oriented model that partitions the policy network into multiple modules and adaptively recombines modules to form specific policies during inference. Specifically, we propose Residual Refined Experts with Instance-level Gating (R2E-IG) to improve cross-distribution generalization. Our contributions are threefold: (1) We introduce a Residual Refined Expert (R2E) architecture that enhance expert expressiveness via residual refinement; (2) We design an instance-level gating mechanism that learns distribution-aware instance representations and routes inputs to suitable modules; (3) We propose a mixed-distribution training mechanism equipped with Dynamic Weight Adaption (DWA), which dynamically reweights training data from different distributions to emphasize more informative ones. Extensive experiments show that R2E-IG achieves competitive performance against state-of-the-art baselines on both in-distribution and out-of-distribution instances across synthetic and benchmark datasets. Moreover, R2E-IG is generic and can be easily integrated into existing DRL-based methods to further improve performance.

Select text to highlight · click a highlight to remove · saved in this browser only
Authors
Changhao Miao, Yuntian Zhang, Tongyu Wu, Fang Deng, Chen Chen
Your notes (browser-local)
saved
arXiv:2605.26776