AutoEP: LLMs-Driven Automation of Hyperparameter Evolution for Metaheuristic Algorithms
This addresses the problem of prohibitive sample complexity and poor generalization in hyperparameter tuning for computational intelligence, offering a novel and accessible paradigm for researchers and practitioners.
The paper tackled the challenge of automating hyperparameter configuration for metaheuristic algorithms by introducing AutoEP, a framework that uses Large Language Models (LLMs) as zero-shot reasoning engines to generate adaptive strategies based on real-time feedback, achieving consistent outperformance over state-of-the-art tuners across diverse benchmarks.
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://anonymous.4open.science/r/AutoEP-3E11