---
title: "局部增强偏好与表征解耦提升跨问题车辆路径规划"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.24859v1"
permalink: "https://feed.astralor.com/items/itm_8bf58d1d05b7119874f8fd23"
published: "2026-08-25T17:44:23.000Z"
score: 75
channel: "ai"
tags: ["PLE","POLAR","偏好优化","多任务学习","表征解耦","车辆路径规划"]
---

# 局部增强偏好与表征解耦提升跨问题车辆路径规划

## AI 点评

> 这是多任务组合优化方向上值得关注的工作。POLAR和PLE分别从训练信号和表征分离两个角度切入，组合后效果明显，适合做物流算法或强化学习研究的读者深入了解。

## 速览

多任务车辆路径规划（VRP）求解器试图在单一统一模型中处理多种VRP变体，以避免为每个变体单独训练模型。现有方法在训练和架构上均存在局限：强化学习面临奖励尺度差异和优势信号萎缩，偏好优化则受限于采样轨迹的同质化；全共享编码器会纠缠异构变体间的约束相关表征。本文提出两个与模型无关的贡献：POLAR训练算法，通过局部搜索细化最佳解码路径后再构造偏好对，获得更具信息量的成对边际；PLE编码器，通过门控机制将每层路由至共享专家和任务特定专家，渐进分离通用路由结构与约束特定编码。在多种VRP变体上的实验表明，POLAR与PLE共同提升了当前神经多任务求解器的性能，在16个分布内变体上平均差距相对最强基线降低21.3%，在27/32个未见变体上优于先前神经方法。

## 关键点

- 提出POLAR训练算法，利用局部搜索细化生成更高信息量的偏好对，缓解偏好优化信号衰减问题
- 提出PLE编码器架构，通过共享专家与任务特定专家的门控路由，解耦通用与约束特定表征
- 在16个分布内VRP变体上相对最强基线平均差距降低21.3%，在32个未见变体上27个优于此前神经方法
- 消融实验证明两项贡献在不同骨干架构上均能提升跨问题泛化能力

## 全文

Multi-task vehicle routing problem (VRP) solvers seek to handle multiple VRP variants within a single unified model, avoiding the need to train a separate model for every variant. In spite of recent progress, current approaches remain limited on two fronts. On the training side, reinforcement learning suffers from reward-scale disparities and shrinking advantage signals as policies improve, whereas preference optimization stagnates once sampled tours become near-identical and thus fundamentally limited by the quality of the policy's own generated solutions, leaving both paradigms with weak supervision as training progresses. On the architecture side, existing fully shared encoders entangle constraint-dependent representations across heterogeneous variants, which limits generalization. We address these gaps with two model-agnostic contributions. First, we propose Preference Optimization with Locally Augmented Refinement (POLAR), a novel training algorithm that applies a local search refinement pass to the best decoded tour before forming preference pairs, yielding much more informative pairwise margins. 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, progressively separating common routing structure from constraint-specific encodings. Through extensive experiments on various VRP variants, we show that POLAR and PLE together elevate the current state-of-the-art among neural multi-task solvers. We reduce the average gap to reference solutions by 21.3% relative to the strongest published baseline on 16 in-distribution variants, and outperform prior neural methods on 27 out of 32 unseen variants. Ablation studies confirm the efficacy of each contribution, showing that both improve cross-problem generalization across multiple backbone model architectures.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_8bf58d1d05b7119874f8fd23