Vehicle Routing Problems (VRPs) are optimization problems with significant real-world implications in logistics, transportation, and supply chain management. Despite the recent progress made in learning to solve individual VRP variants, there is a lack of a unified approach that can effectively tackle a wide range of tasks, which is crucial for real-world impact. This paper introduces RouteFinder, a framework for developing foundation models for VRPs. Our key idea is that a foundation model for VRPs should be able to model variants by treating each variant as a subset of a larger VRP problem, equipped with different attributes. We introduce a parallelized environment that can handle any combination of attributes at the same time in a batched manner, and an efficient sampling procedure to train on a mix of problems at each optimization step that can greatly improve convergence robustness. We also introduce novel Global Feature Embeddings that project instance-wise attributes efficiently onto the latent space and help the model understand different VRP variants. Finally, we introduce Efficient Adapter Layers, a simple yet effective technique to finetune pre-trained RouteFinder models to solve novel variants with previously unseen attributes outside of the original feature space. We validate our approach through extensive experiments on 24 VRP variants, demonstrating competitive results over recent multi-task learning models. We make our code openly available at https://github.com/ai4co/routefinder.

翻译：车辆路径问题（VRPs）是一类在物流、运输和供应链管理领域具有重要现实意义的优化问题。尽管近期在学习求解单个VRP变体方面取得了进展，但仍缺乏能够有效处理广泛任务范围的统一方法，而这对于实际应用至关重要。本文提出了RouteFinder——一个用于开发VRP基础模型的框架。我们的核心思想是：VRP基础模型应能通过将每个变体视为具备不同属性的更大规模VRP问题的子集来建模各类变体。我们设计了一种并行化环境，能够以批处理方式同时处理任意属性组合；并提出一种高效的采样流程，在每个优化步骤中对混合问题进行训练，从而显著提升收敛鲁棒性。此外，我们提出了新颖的全局特征嵌入方法，将实例级属性高效映射到潜在空间，帮助模型理解不同的VRP变体。最后，我们引入了高效适配器层——这是一种简单而有效的技术，可用于微调预训练的RouteFinder模型，以解决原始特征空间之外具有未见属性的新型变体。我们在24种VRP变体上进行了大量实验验证，结果表明该方法相较于近期多任务学习模型具有竞争优势。代码已开源：https://github.com/ai4co/routefinder。