---
title: "A Unified Knowledge Embedded Reinforcement Learning-based Framework for Generalized Capacitated Vehicle Routing Problems"
authors:
  - "Wen Wang"
  - "Xiangchen Wu"
  - "Liang Wang"
  - "Hao Hu"
  - "Xianping Tao"
doi: "10.24963/ijcai.2026/691"
url: "https://ijcai.org/proceedings/2026/691"
pdf: "https://ijcai.org/proceedings/2026/0691.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "6208-6216"
track: "Main Track"
keywords:
  - "Planning and Scheduling: Applications"
  - "Planning and Scheduling: Learning in planning and scheduling"
---

# A Unified Knowledge Embedded Reinforcement Learning-based Framework for Generalized Capacitated Vehicle Routing Problems

Wen Wang, Xiangchen Wu, Liang Wang, Hao Hu, Xianping Tao

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 6208-6216. DOI: [10.24963/ijcai.2026/691](https://doi.org/10.24963/ijcai.2026/691)

## Abstract

The Capacitated Vehicle Routing Problem (CVRP) is a fundamental NP-hard problem with broad applications in logistics and transportation. Real-world CVRPs often involve diverse objectives and complex constraints, such as time windows or backhaul requirements, motivating the development of a unified solution framework.
Recent reinforcement learning (RL) approaches have shown promise in combinatorial optimization, yet they rely on end-to-end learning and lack explicit problem-solving knowledge, limiting solution quality.
In this paper, we propose a knowledge-embedded framework inspired by the Route-First Cluster-Second heuristics. 
It incorporates knowledge at two levels: (1) decomposing CVRPs into the route-first and cluster-second subproblems, and (2) leveraging dynamic programming to solve the second subproblem, whose results guide the RL-based constructive solver to solve the first problem.
To mitigate partial observability caused by problem decomposition, we introduce a unified history-enhanced context processing module. 
Extensive experiments show that this framework achieves superior solution quality compared with state-of-the-art learning-based methods, with a smaller gap to classical heuristics, demonstrating strong generalization across diverse CVRP variants.