Saved in:
Bibliographic Details
Main Authors: Xu, Zhenxing, Zhang, Yizhe, Bao, Weidong, Wang, Hao, Chen, Ming, Ye, Haoran, Jiang, Wenzheng, Yan, Hui, Wang, Ji
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.23189
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911516735832064
author Xu, Zhenxing
Zhang, Yizhe
Bao, Weidong
Wang, Hao
Chen, Ming
Ye, Haoran
Jiang, Wenzheng
Yan, Hui
Wang, Ji
author_facet Xu, Zhenxing
Zhang, Yizhe
Bao, Weidong
Wang, Hao
Chen, Ming
Ye, Haoran
Jiang, Wenzheng
Yan, Hui
Wang, Ji
contents Dynamically configuring algorithm hyperparameters is a fundamental challenge in computational intelligence. While learning-based methods offer automation, they suffer from prohibitive sample complexity and poor generalization. We introduce AutoEP, a novel framework that bypasses training entirely by leveraging Large Language Models (LLMs) as zero-shot reasoning engines for algorithm control. AutoEP's core innovation lies in a tight synergy between two components: (1) an online Exploratory Landscape Analysis (ELA) module that provides real-time, quantitative feedback on the search dynamics, and (2) a multi-LLM reasoning chain that interprets this feedback to generate adaptive hyperparameter strategies. This approach grounds high-level reasoning in empirical data, mitigating hallucination. Evaluated on three distinct metaheuristics across diverse combinatorial optimization benchmarks, AutoEP consistently outperforms state-of-the-art tuners, including neural evolution and other LLM-based methods. Notably, our framework enables open-source models like Qwen3-30B to match the performance of GPT-4, demonstrating a powerful and accessible new paradigm for automated hyperparameter design. Our code is available at https://github.com/YiZheZhang12/AutoEP.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23189
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AutoEP: LLMs-Driven Automation of Hyperparameter Evolution for Metaheuristic Algorithms
Xu, Zhenxing
Zhang, Yizhe
Bao, Weidong
Wang, Hao
Chen, Ming
Ye, Haoran
Jiang, Wenzheng
Yan, Hui
Wang, Ji
Artificial Intelligence
Dynamically configuring algorithm hyperparameters is a fundamental challenge in computational intelligence. While learning-based methods offer automation, they suffer from prohibitive sample complexity and poor generalization. We introduce AutoEP, a novel framework that bypasses training entirely by leveraging Large Language Models (LLMs) as zero-shot reasoning engines for algorithm control. AutoEP's core innovation lies in a tight synergy between two components: (1) an online Exploratory Landscape Analysis (ELA) module that provides real-time, quantitative feedback on the search dynamics, and (2) a multi-LLM reasoning chain that interprets this feedback to generate adaptive hyperparameter strategies. This approach grounds high-level reasoning in empirical data, mitigating hallucination. Evaluated on three distinct metaheuristics across diverse combinatorial optimization benchmarks, AutoEP consistently outperforms state-of-the-art tuners, including neural evolution and other LLM-based methods. Notably, our framework enables open-source models like Qwen3-30B to match the performance of GPT-4, demonstrating a powerful and accessible new paradigm for automated hyperparameter design. Our code is available at https://github.com/YiZheZhang12/AutoEP.
title AutoEP: LLMs-Driven Automation of Hyperparameter Evolution for Metaheuristic Algorithms
topic Artificial Intelligence
url https://arxiv.org/abs/2509.23189