Saved in:
Bibliographic Details
Main Authors: Wang, Hui, Zhang, Xufeng, Mu, Chaoxu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.11422
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913902733819904
author Wang, Hui
Zhang, Xufeng
Mu, Chaoxu
author_facet Wang, Hui
Zhang, Xufeng
Mu, Chaoxu
contents Heuristics have achieved great success in solving combinatorial optimization problems~(COPs). However, heuristics designed by humans require too much domain knowledge and testing time. Since Large Language Models~(LLMs) possess strong capabilities to understand and generate content with a knowledge base that covers various domains, they offer potential ways to automatically optimize heuristics. To this end, we propose Planning of Heuristics~(PoH), an optimization method that integrates LLM self-reflection with Monte Carlo Tree Search, a well-known planning algorithm. PoH iteratively refines generated heuristics by evaluating their performance and providing improvement suggestions. Our method enables to iteratively evaluate the generated heuristics~(states) and improve them based on the improvement suggestions~(actions) and evaluation results~(rewards), by effectively simulating future states to search for paths with higher rewards. In this paper, we apply PoH to solve the Traveling Salesman Problem and the Flow Shop Scheduling Problem. The experimental results show that PoH outperforms hand-crafted heuristics and other Automatic Heuristic Design methods based on LLMs, and achieves the state-of-the-art performance in automating heuristic optimization with LLMs to solve tested COPs, especially with large sizes.
format Preprint
id arxiv_https___arxiv_org_abs_2502_11422
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Planning of Heuristics: Strategic Planning on Large Language Models with Monte Carlo Tree Search for Automating Heuristic Optimization
Wang, Hui
Zhang, Xufeng
Mu, Chaoxu
Artificial Intelligence
Heuristics have achieved great success in solving combinatorial optimization problems~(COPs). However, heuristics designed by humans require too much domain knowledge and testing time. Since Large Language Models~(LLMs) possess strong capabilities to understand and generate content with a knowledge base that covers various domains, they offer potential ways to automatically optimize heuristics. To this end, we propose Planning of Heuristics~(PoH), an optimization method that integrates LLM self-reflection with Monte Carlo Tree Search, a well-known planning algorithm. PoH iteratively refines generated heuristics by evaluating their performance and providing improvement suggestions. Our method enables to iteratively evaluate the generated heuristics~(states) and improve them based on the improvement suggestions~(actions) and evaluation results~(rewards), by effectively simulating future states to search for paths with higher rewards. In this paper, we apply PoH to solve the Traveling Salesman Problem and the Flow Shop Scheduling Problem. The experimental results show that PoH outperforms hand-crafted heuristics and other Automatic Heuristic Design methods based on LLMs, and achieves the state-of-the-art performance in automating heuristic optimization with LLMs to solve tested COPs, especially with large sizes.
title Planning of Heuristics: Strategic Planning on Large Language Models with Monte Carlo Tree Search for Automating Heuristic Optimization
topic Artificial Intelligence
url https://arxiv.org/abs/2502.11422