OD-Gear: Online Decomposition and Group Sampling for Expert-Guided Adversarial Routing in Scalable Capacitated Vehicle Routing
School of Information Science（信息科学学院）；Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation, Department of CSE, SUSTech, Shenzhen 518055, P. R. China（脑启发智能计算广东省重点实验室、计算机科学与工程系、南方科技大学、深圳518055，中华人民共和国）
Dongbin Jiao, Zisheng Chen, Xianyi Wang, Jintao Shi, Shengcai Liu, Shi Yan
Solving large-scale capacitated vehicle routing problems (CVRP) is hindered by the high complexity of classical heuristics and the limited generalization of neural solvers. To bridge this gap, we propose OD-Gear, an expert-guided adversarial framework that integrates hybrid genetic search (HGS) and online barycenter clustering (BCC) decomposition with group-relative optimization. OD-Gear internalizes expert heuristics into a graph attention network (GAT)-based policy via high-fidelity knowledge distillation. Our minimax adversarial training distills divide-and-conquer strategies into dense surrogate rewards, while a group-sampling strategy exploits relative solution advantages to promote both diversity and quality. This architecture enables high-quality, clustering-free inference on massive graphs, effectively bypassing the overhead of traditional decomposition. Empirical results demonstrate that OD-Gear achieves state-of-the-art (SOTA) performance across most benchmarks, remaining highly competitive at the 10,000-node scale. By providing heuristic-quality solutions with low-latency, OD-Gear offers a robust and scalable framework for large-scale CVRP.
Deep Reinforcement Learning for Solving the Heterogeneous Capacitated Vehicle Routing Problem
National University of Singapore（新加坡国立大学）；Singapore Institute of Manufacturing Technology（新加坡制造技术研究院）；Southwest Jiaotong University（西南交通大学）；Shandong University（山东大学）；Nanyang Technological University（南洋理工大学）
Towards Omni-generalizable Neural Methods for Vehicle Routing Problems
Nanyang Technological University（南洋理工大学）；Eindhoven University of Technology（埃因霍温理工大学）；Shandong University（山东大学）；Singapore Management University（新加坡管理大学）
Neural Networks for Local Search and Crossover in Vehicle Routing: A Possible Overkill?
Pontifical Catholic University of Rio de Janeiro（里约热内卢天主教大学）；Jacobs Technion-Cornell Institute（雅各布斯泰克尼昂-康奈尔研究所）；Cornell Tech（康奈尔理工学院）；Technion - IIT（以色列理工学院）
Adversarial Generative Flow Network for Solving Vehicle Routing Problems
Singapore Management University（新加坡管理大学）；Singapore Institute of Manufacturing Technology (SIMTech), Agency of Science, Technology and Research (A*STAR)（新加坡制造技术研究院（新加坡科技研究局下属机构））
Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformer
National University of Singapore（新加坡国立大学）；University of Electronic Science and Technology of China（电子科技大学）；Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究院）；The Hong Kong University of Science and Technology（香港科技大学）；Singapore Institute of Manufacturing Technology, A*STAR（新加坡科技研究局新加坡制造技术研究院）；Shandong University（山东大学）
A Deep Reinforcement Learning Approach for Solving the Traveling Salesman Problem with Drone
Suleyman Demirel University（苏莱曼·德米雷尔大学）；UNIST（蔚山科学技术院）；Korea University（高丽大学）；Amazon（亚马逊）；University of South Florida（南佛罗里达大学）
强化学习最近在许多组合最优化问题的学习质量解决方案中显示出了希望。特别是，基于注意力的编码器-解码器模型在各种路由问题上表现出很高的效率，包括流动推销员问题（TSP）。不幸的是，它们在TSP with Drone（TSP-D）中表现不佳，需要协调不同的车辆-卡车和无人机。在TSP-D中，两辆车一前一后地移动，并且可能需要在节点处等待另一辆车加入。基于注意力的无状态解码器无法在车辆之间进行这种协调。我们提出了一个混合模型，它使用注意编码器和长短期记忆（LSTM）网络解码器，其中解码器的隐藏状态可以表示所做的动作序列。我们的经验表明，这样的混合模型提高了一个纯粹的基于注意力的模型的解决方案的质量和计算效率。最小-最大容量限制车辆路径问题（mmCVRP）的实验结果也表明，混合模型比基于注意力的模型更适合于多车辆的协调路径问题。所提出的模型展示了与运筹学基线方法相当的结果。
