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

• URL: http://arxiv.org/abs/2605.26776v1
• Date: Tue, 26 May 2026 09:46:54 GMT
• Title: Towards Generalization-Oriented Models for Vehicle Routing Problems with Mixture-of-Experts
• Abstract summary: We propose Residual Refined Experts with Instance-level Gating (R2E-IG) to improve cross-distribution generalization.<n>R2E-IG achieves competitive performance against state-of-the-art baselines on both in-distribution and out-of-distribution instances.
• Score: 8.616895584914579
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Improving Cross-Problem Vehicle Routing with Locally Augmented Preferences and Representation Disentanglement [0.0]
  Multi-task vehicle routing problem (VRP) solvers seek to handle multiple VRP variants within a single unified model.<n>We propose a novel training algorithm that applies a local search refinement pass to the best decoded tour before forming preference pairs.<n>Second, a Progressive Layered Extraction (PLE) encoder routes each encoder layer through one shared expert and a set of task-specific experts via a gating mechanism.
  arXiv  Detail & Related papers  (2026-08-25T17:44:23Z)
• HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving [51.268878540511054]
  We propose HAD, an end-to-end planning framework with a Hierarchical Diffusion Policy.<n>We show that HAD achieves new state-of-the-art performance on both NAVSIM and HUGSIM.
  arXiv  Detail & Related papers  (2026-04-04T04:12:47Z)
• Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration [49.9937230730202]
  We propose Search-R2, a novel Actor-Refiner collaboration framework that enhances reasoning through targeted intervention.<n>Our approach decomposes the generation process into an Actor, which produces initial reasoning trajectories.<n>We show that Search-R2 consistently outperforms strong RAG and RL-based baselines across model scales.
  arXiv  Detail & Related papers  (2026-02-03T15:32:09Z)
• Sample-Efficient Neurosymbolic Deep Reinforcement Learning [49.60927398960061]
  We propose a neuro-symbolic Deep RL approach that integrates background symbolic knowledge to improve sample efficiency.<n>Online reasoning is performed to guide the training process through two mechanisms.<n>We show improved performance over a state-of-the-art reward machine baseline.
  arXiv  Detail & Related papers  (2026-01-06T09:28:53Z)
• FedDSR: Federated Deep Supervision and Regularization Towards Autonomous Driving [32.600054594223096]
  Federated Deep Supervision and Regularization (FedDSR) is a paradigm that incorporates multi-access intermediate layer supervision and regularization within federated AD system.<n>FedDSR achieves up to 8.93% improvement in mIoU and 28.57% reduction in training rounds, compared to other Federated Learning baselines.
  arXiv  Detail & Related papers  (2025-12-07T06:23:59Z)
• Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its Friends [64.71326476563213]
  Off-policy reinforcement learning for large language models (LLMs) is attracting growing interest.<n>We present a first-principles derivation for grouprelative REINFORCE without assuming a specific training data distribution.<n>This perspective yields two general principles for adapting REINFORCE to off-policy settings.
  arXiv  Detail & Related papers  (2025-09-29T02:34:54Z)
• Generalization in Reinforcement Learning for Radio Access Networks [2.9822261313236513]
  We propose a generalization-centered RL framework for RAN control.<n>It robustly reconstructs dynamically varying states from partial and noisy observations.<n>It encodes static and semi-static information, such as radio nodes, cell attributes, and their topology, through graph representations.
  arXiv  Detail & Related papers  (2025-07-09T07:22:22Z)
• Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs [51.21041884010009]
  Ring-lite is a Mixture-of-Experts (MoE)-based large language model optimized via reinforcement learning (RL)<n>Our approach matches the performance of state-of-the-art (SOTA) small-scale reasoning models on challenging benchmarks.
  arXiv  Detail & Related papers  (2025-06-17T17:12:34Z)
• GRAM: Generalization in Deep RL with a Robust Adaptation Module [62.662894174616895]
  In this work, we present a framework for dynamics generalization in deep reinforcement learning.<n>We introduce a robust adaptation module that provides a mechanism for identifying and reacting to both in-distribution and out-of-distribution environment dynamics.<n>Our algorithm GRAM achieves strong generalization performance across in-distribution and out-of-distribution scenarios upon deployment.
  arXiv  Detail & Related papers  (2024-12-05T16:39:01Z)
• Improving Generalization of Neural Vehicle Routing Problem Solvers Through the Lens of Model Architecture [9.244633039170186]
  We propose a plug-and-play Entropy-based Scaling Factor (ESF) and a Distribution-Specific (DS) decoder.<n>ESF adjusts the attention weight pattern of the model towards familiar ones discovered during training when solving VRPs of varying sizes.<n>DS decoder explicitly models VRPs of multiple training distribution patterns through multiple auxiliary light decoders, expanding the model representation space.
  arXiv  Detail & Related papers  (2024-06-10T09:03:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.