<ul><li>SPIO is a framework that leverages Large Language Models (LLMs) for orchestration of multi-agent planning in automated data science.</li><li>SPIO consists of four key modules: data preprocessing, feature engineering, modeling, and hyperparameter tuning.</li><li>Dedicated planning agents generate candidate strategies in each module, leading to comprehensive exploration.</li><li>SPIO offers two variants: SPIO-S, which selects the best solution path determined by LLM; and SPIO-E, which ensembles the top k candidate plans for improved predictive performance.</li></ul>

SPIO: Ensemble and Selective Strategies via LLM-Based Multi-Agent Planning in Automated Data Science

Discover more