用大模型零样本推理实现元启发式算法超参数自动演化，无需训练即可高效调参。
AutoEP: LLMs-Driven Automation of Hyperparameter Evolution for Metaheuristic Algorithms
- 利用大模型做零样本推理，结合实时搜索动态分析生成自适应调参策略。
- 在多个组合优化任务上优于现有先进方法，开源模型性能接近GPT-4。
- 适用于希望免训练自动化调参的研究者与工程实践者。
动态配置算法超参数是计算智能中的核心挑战。尽管基于学习的方法可实现自动化，但存在样本复杂度高、泛化能力差的问题。我们提出AutoEP，一种完全无需训练的新框架，通过大语言模型（LLMs）作为零样本推理引擎实现算法控制。其核心创新在于两个模块的紧密协同：(1) 在线探索性景观分析（ELA）模块，实时提供搜索动态的量化反馈；(2) 多大模型推理链，解析该反馈并生成自适应超参数策略。该方法将高层推理建立在实证数据基础上，有效缓解幻觉问题。在三种不同元启发式算法和多个组合优化基准上的评估显示，AutoEP持续优于当前最先进调参器，包括神经进化和其他基于大模型的方法。值得注意的是，本框架使开源模型如Qwen3-30B达到与GPT-4相当的性能，展示了强大且可访问的自动化超参数设计新范式。代码已公开于 https://github.com/YiZheZhang12/AutoEP。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。