LLM-Driven Joint Evolution of Coupled Heuristics Components for Routing Optimization

2026-09-02

AI Summary

本文提出LLM-HCJG框架，通过联合生成和协同进化互依赖的启发式组件解决组合优化问题，尤其在路径优化中表现优异。

Abstract

Heuristic design for combinatorial optimization remains heavily reliant on expert knowledge, while existing large language model (LLM)-enhanced evolutionary methods typically evolve isolated algorithmic components, even when one determines the search state on which another operates. This paper proposes LLM-driven Heuristic Components Joint Generation (LLM-HCJG), a population-based framework that jointly generates and co-evolves interdependent heuristic components under a shared design blueprint. Applied to guided local search (GLS), LLM-HCJG couples solution initialization with penalty construction and embeds the generated pair into an enhanced online search mechanism. The resulting form is further transferred from the traveling salesman problem (TSP) to the capacitated vehicle routing problem (CVRP). Theoretical analysis establishes the non-separable state-transition effects between the two components and the advantage in generation consistency. Across synthetic instances and 41 public TSPLIB/CVRPLIB benchmarks, LLM-HCJG attains consistently low optimality gaps, including best or tied-best results on 28 of 29 TSPLIB instances and all 12 CVRPLIB instances. Ablation and structural analyses further indicate that these gains are associated with cross-component compatibility and alignment rather than isolated-component recombination. These results support effective cross-instance transfer within the evaluated routing settings under limited-sample, modest-cost training.

Problem

• Heuristic Design
• Combinatorial Optimization
• Large Language Model (LLM)
• Evolutionary Methods
• Interdependent Components

Innovation

• LLM-driven Heuristic Components Joint Generation (LLM-HCJG)
• co-evolve interdependent heuristic components
• guided local search (GLS)
• cross-component compatibility and alignment
• transfer learning