Large Language Model Aided Multi-objective Evolutionary Algorithm: a Low-cost Adaptive Approach
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916421907251200 |
|---|---|
| author | Liu, Wanyi Chen, Long Tang, Zhenzhou |
| author_facet | Liu, Wanyi Chen, Long Tang, Zhenzhou |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_02301 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Large Language Model Aided Multi-objective Evolutionary Algorithm: a Low-cost Adaptive Approach Liu, Wanyi Chen, Long Tang, Zhenzhou Neural and Evolutionary Computing 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. |
| title | Large Language Model Aided Multi-objective Evolutionary Algorithm: a Low-cost Adaptive Approach |
| topic | Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2410.02301 |