Enhancing CVRP Solver through LLM-driven Automatic Heuristic Design

2026-02-26

AI Summary

This study addresses the challenge of balancing solution quality and computational efficiency in large-scale Capacitated Vehicle Routing Problems (CVRP). To this end, it proposes AILS-AHD, a novel approach that integrates large language models (LLMs) into CVRP solving for the first time. Within an Adaptive Iterated Local Search (AILS) framework, the method dynamically generates and refines destruction heuristics using LLM-driven guidance, combining accelerated search mechanisms with evolutionary optimization. Evaluated on the large-scale CVRPLib benchmark suite, AILS-AHD establishes new best-known solutions for 8 out of 10 instances, significantly outperforming state-of-the-art solvers such as AILS-II and HGS. This work demonstrates a promising pathway toward automated and intelligent heuristic design for complex combinatorial optimization problems.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Heuristic Search
• Computer Vision: Learning & Optimization for CV

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

The Capacitated Vehicle Routing Problem (CVRP), a fundamental combinatorial optimization challenge, focuses on optimizing fleet operations under vehicle capacity constraints. While extensively studied in operational research, the NP-hard nature of CVRP continues to pose significant computational challenges, particularly for large-scale instances. This study presents AILS-AHD (Adaptive Iterated Local Search with Automatic Heuristic Design), a novel approach that leverages Large Language Models (LLMs) to revolutionize CVRP solving. Our methodology integrates an evolutionary search framework with LLMs to dynamically generate and optimize ruin heuristics within the AILS method. Additionally, we introduce an LLM-based acceleration mechanism to enhance computational efficiency. Comprehensive experimental evaluations against state-of-the-art solvers, including AILS-II and HGS, demonstrate the superior performance of AILS-AHD across both moderate and large-scale instances. Notably, our approach establishes new best-known solutions for 8 out of 10 instances in the CVRPLib large-scale benchmark, underscoring the potential of LLM-driven heuristic design in advancing the field of vehicle routing optimization.

Problem

• Capacitated Vehicle Routing Problem
• CVRP
• combinatorial optimization
• NP-hard
• large-scale instances

Innovation

• Large Language Models
• Automatic Heuristic Design
• Capacitated Vehicle Routing Problem
• Adaptive Iterated Local Search
• Evolutionary Search