SPIO: Ensemble and Selective Strategies via LLM-Based Multi-Agent Planning in Automated Data Science
Year: 2026
Type: conference-paper
Abstract: Large Language Models (LLMs) have enabled dynamic reasoning in automated data analytics, yet recent multi-agent systems remain limited by rigid, single-path workflows that restrict strategic exploration and often lead to suboptimal outcomes.To overcome these limitations, we propose SPIO (Sequential Plan Integration and Optimization), a framework that replaces rigid workflows with adaptive, multi-path planning across four core modules: data preprocessing, feature engineering, model selection, and hyperparameter tuning.In each module, specialized agents generate diverse candidate strategies, which are cascaded and refined by an optimization agent.SPIO offers two operating modes: SPIO-S for selecting a single optimal pipeline, and SPIO-E for ensembling top-k pipelines to maximize robustness.Extensive evaluations on Kaggle and OpenML benchmarks show that SPIO consistently outperforms state-of-the-art baselines, achieving an average performance gain of 5.6%.By explicitly exploring and integrating multiple solution paths, SPIO delivers a more flexible, accurate, and reliable foundation for automated data science.* denotes equal contribution.† denotes corresponding author(s).
Authors: Wonduk Seo, Juhyeon Lee, Yanjun Shao, Qingshan Zhou, Seunghyun Lee, Yi Bu
Institutions: Peking University, Yale University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Awards: G1859020638, G394832172
OpenAlex ID: W4417069047