用三个AI智能体协作，高效优化机器学习超参数。
OptiMindTune: A Multi-Agent Framework for Intelligent Hyperparameter Optimization
- 三类AI代理分工协作：推荐、评估与决策。
- 基于Gemini模型实现智能搜索，提升调优效率。
- 适合需要自动化调参的科研与工程人员。
超参数优化（HPO）是机器学习模型开发中关键但具挑战性的环节，显著影响模型性能与泛化能力。传统HPO方法在高维空间、复杂依赖关系和计算成本方面面临困难。本文提出OptiMindTune，一种新型多智能体框架，旨在智能高效地优化超参数。该框架融合三个专用AI代理——推荐代理、评估代理和决策代理，均基于Google Gemini模型，分别负责模型选择与超参数建议、稳健评估及策略决策。通过动态交互与知识共享，OptiMindTune相比单智能体或整体式方法能更快速、更鲁棒地收敛至最优配置。框架结合大语言模型与自适应搜索机制，实现可扩展的智能自动机器学习。我们认为，多智能体范式为应对现代机器学习调参日益增长的复杂性提供了有前景的路径。
原文摘要 · Abstract (English)
Hyperparameter optimization (HPO) is a critical yet challenging aspect of machine learning model development, significantly impacting model performance and generalization. Traditional HPO methods often struggle with high dimensionality, complex interdependencies, and computational expense. This paper introduces OptiMindTune, a novel multi-agent framework designed to intelligently and efficiently optimize hyperparameters. OptiMindTune leverages the collaborative intelligence of three specialized AI agents -- a Recommender Agent, an Evaluator Agent, and a Decision Agent -- each powered by Google's Gemini models. These agents address distinct facets of the HPO problem, from model selection and hyperparameter suggestion to robust evaluation and strategic decision-making. By fostering dynamic interactions and knowledge sharing, OptiMindTune aims to converge to optimal hyperparameter configurations more rapidly and robustly than existing single-agent or monolithic approaches. Our framework integrates principles from advanced large language models, and adaptive search to achieve scalable and intelligent AutoML. We posit that this multi-agent paradigm offers a promising avenue for tackling the increasing complexity of modern machine learning model tuning.
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。