Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Fei, Tong, Xialiang, Yuan, Mingxuan, Lin, Xi, Luo, Fu, Wang, Zhenkun, Lu, Zhichao, Zhang, Qingfu
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909214310400000
author Liu, Fei
Tong, Xialiang
Yuan, Mingxuan
Lin, Xi
Luo, Fu
Wang, Zhenkun
Lu, Zhichao
Zhang, Qingfu
author_facet Liu, Fei
Tong, Xialiang
Yuan, Mingxuan
Lin, Xi
Luo, Fu
Wang, Zhenkun
Lu, Zhichao
Zhang, Qingfu
contents Heuristics are widely used for dealing with complex search and optimization problems. However, manual design of heuristics can be often very labour extensive and requires rich working experience and knowledge. This paper proposes Evolution of Heuristic (EoH), a novel evolutionary paradigm that leverages both Large Language Models (LLMs) and Evolutionary Computation (EC) methods for Automatic Heuristic Design (AHD). EoH represents the ideas of heuristics in natural language, termed thoughts. They are then translated into executable codes by LLMs. The evolution of both thoughts and codes in an evolutionary search framework makes it very effective and efficient for generating high-performance heuristics. Experiments on three widely studied combinatorial optimization benchmark problems demonstrate that EoH outperforms commonly used handcrafted heuristics and other recent AHD methods including FunSearch. Particularly, the heuristic produced by EoH with a low computational budget (in terms of the number of queries to LLMs) significantly outperforms widely-used human hand-crafted baseline algorithms for the online bin packing problem.
format Preprint
id arxiv_https___arxiv_org_abs_2401_02051
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model
Liu, Fei
Tong, Xialiang
Yuan, Mingxuan
Lin, Xi
Luo, Fu
Wang, Zhenkun
Lu, Zhichao
Zhang, Qingfu
Neural and Evolutionary Computing
Artificial Intelligence
Heuristics are widely used for dealing with complex search and optimization problems. However, manual design of heuristics can be often very labour extensive and requires rich working experience and knowledge. This paper proposes Evolution of Heuristic (EoH), a novel evolutionary paradigm that leverages both Large Language Models (LLMs) and Evolutionary Computation (EC) methods for Automatic Heuristic Design (AHD). EoH represents the ideas of heuristics in natural language, termed thoughts. They are then translated into executable codes by LLMs. The evolution of both thoughts and codes in an evolutionary search framework makes it very effective and efficient for generating high-performance heuristics. Experiments on three widely studied combinatorial optimization benchmark problems demonstrate that EoH outperforms commonly used handcrafted heuristics and other recent AHD methods including FunSearch. Particularly, the heuristic produced by EoH with a low computational budget (in terms of the number of queries to LLMs) significantly outperforms widely-used human hand-crafted baseline algorithms for the online bin packing problem.
title Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model
topic Neural and Evolutionary Computing
Artificial Intelligence
url https://arxiv.org/abs/2401.02051