Large Language Model Aided Multi-objective Evolutionary Algorithm: a Low-cost Adaptive Approach

TL;DR

This paper introduces a novel framework combining large language models with multi-objective evolutionary algorithms to improve convergence speed and solution quality while reducing manual tuning and interaction costs.

Contribution

It presents an adaptive and hybrid framework that integrates LLMs into MOEAs, enhancing search capabilities and generalization with minimal interaction costs.

Findings

Accelerated convergence of MOEA with LLM integration

High-quality solutions generated by adaptive prompt mechanisms

Reduced manual tuning and interaction costs

Abstract

Multi-objective optimization is a common problem in practical applications, and multi-objective evolutionary algorithm (MOEA) is considered as one of the effective methods to solve these problems. However, their randomness sometimes prevents algorithms from rapidly converging to global optimization, and the design of their genetic operators often requires complicated manual tuning. To overcome this challenge, this study proposes a new framework that combines a large language model (LLM) with traditional evolutionary algorithms to enhance the algorithm's search capability and generalization performance.In our framework, we employ adaptive and hybrid mechanisms to integrate the LLM with the MOEA, thereby accelerating algorithmic convergence. Specifically, we leverage an auxiliary evaluation function and automated prompt construction within the adaptive mechanism to flexibly adjust the utilization of the LLM, generating high-quality solutions that are further refined and optimized through genetic operators.Concurrently, the hybrid mechanism aims to minimize interaction costs with the LLM as much as possible.