Chain-of-Context Learning: Dynamic Constraint Understanding for Multi-Task VRPs

2026-03-02

AI Summary

This work addresses the limited generalization of existing methods in multi-task vehicle routing problems (VRPs), which struggle to dynamically perceive and adapt to evolving constraints and node states. To overcome this, we propose a Chain-based Contextual Learning (CCL) framework that incorporates a Relevance-Guided Context Reconstruction (RGCR) module to model dynamic constraints in real time, along with a Trajectory-Shared Node Re-embedding (TSNR) mechanism to enhance cross-task generalization. Evaluated across 48 VRP variants, CCL consistently outperforms state-of-the-art approaches on all 16 in-distribution tasks and the majority of 32 out-of-distribution tasks, demonstrating significant improvements in solving multi-task VRPs.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Computer Vision: Learning & Optimization for CV

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Multi-task Vehicle Routing Problems (VRPs) aim to minimize routing costs while satisfying diverse constraints. Existing solvers typically adopt a unified reinforcement learning (RL) framework to learn generalizable patterns across tasks. However, they often overlook the constraint and node dynamics during the decision process, making the model fail to accurately react to the current context. To address this limitation, we propose Chain-of-Context Learning (CCL), a novel framework that progressively captures the evolving context to guide fine-grained node adaptation. Specifically, CCL constructs step-wise contextual information via a Relevance-Guided Context Reformulation (RGCR) module, which adaptively prioritizes salient constraints. This context then guides node updates through a Trajectory-Shared Node Re-embedding (TSNR) module, which aggregates shared node features from all trajectories' contexts and uses them to update inputs for the next step. By modeling evolving preferences of the RL agent, CCL captures step-by-step dependencies in sequential decision-making. We evaluate CCL on 48 diverse VRP variants, including 16 in-distribution and 32 out-of-distribution (with unseen constraints) tasks. Experimental results show that CCL performs favorably against the state-of-the-art baselines, achieving the best performance on all in-distribution tasks and the majority of out-of-distribution tasks.

Problem

• Multi-task Vehicle Routing Problems
• constraint dynamics
• context awareness
• sequential decision-making
• node adaptation

Innovation

• Chain-of-Context Learning
• Relevance-Guided Context Reformulation
• Trajectory-Shared Node Re-embedding
• Multi-task VRP
• Dynamic Constraint Understanding