让大模型像专家一样一步步优化机器学习流程，效果更稳更好
IMPROVE: Iterative Model Pipeline Refinement and Optimization Leveraging LLM Experts
- 大模型分步迭代优化管道各组件，不一次性改全部
- 在多个数据集上表现优于现有零样本方法
- 适合想自动化模型调优的研究者和工程师
大语言模型代理已成自动化机器学习工作流的有前景方案，但现有方法多在评估前一次性优化整个流程，难以定位改进来源，导致优化不稳定、收敛慢。为此，我们提出迭代精炼策略，受人类机器学习专家启发，聚焦逐个组件改进而非整体突变。通过基于真实训练反馈系统性更新各组件，该策略显著提升模型性能，并提供理论支持其优越性。我们进一步将该策略集成至IMPROVE——一个端到端的大模型代理框架，用于自动化与优化目标分类流程。在不同规模和领域的数据集上广泛评估表明，迭代精炼使IMPROVE持续优于现有零样本大模型方法。
原文摘要 · Abstract (English)
Large language model (LLM) agents have emerged as a promising solution to automate the workflow of machine learning, but most existing methods share a common limitation: they attempt to optimize entire pipelines in a single step before evaluation, making it difficult to attribute improvements to specific changes. This lack of granularity leads to unstable optimization and slower convergence, limiting their effectiveness. To address this, we introduce Iterative Refinement, a novel strategy for LLM-driven ML pipeline design inspired by how human ML experts iteratively refine models, focusing on one component at a time rather than making sweeping changes all at once. By systematically updating individual components based on real training feedback, Iterative Refinement improves overall model performance. We also provide some theoretical edvience of the superior properties of this Iterative Refinement. Further, we implement this strategy in IMPROVE, an end-to-end LLM agent framework for automating and optimizing object classification pipelines. Through extensive evaluations across datasets of varying sizes and domains, we demonstrate that Iterative Refinement enables IMPROVE to consistently achieve better performance over existing zero-shot LLM-based approaches.
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。