AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions
This work addresses the problem of automating data pipelines for data scientists, offering a customizable tool that integrates human expertise, but it appears incremental as it builds on existing multi-agent and toolkit approaches.
The paper tackles the challenge of automating complex data science tasks for tabular data by proposing AutoKaggle, a multi-agent framework that assists data scientists, achieving a validation submission rate of 0.85 and a comprehensive score of 0.82 in evaluations on Kaggle competitions.
Data science tasks involving tabular data present complex challenges that require sophisticated problem-solving approaches. We propose AutoKaggle, a powerful and user-centric framework that assists data scientists in completing daily data pipelines through a collaborative multi-agent system. AutoKaggle implements an iterative development process that combines code execution, debugging, and comprehensive unit testing to ensure code correctness and logic consistency. The framework offers highly customizable workflows, allowing users to intervene at each phase, thus integrating automated intelligence with human expertise. Our universal data science toolkit, comprising validated functions for data cleaning, feature engineering, and modeling, forms the foundation of this solution, enhancing productivity by streamlining common tasks. We selected 8 Kaggle competitions to simulate data processing workflows in real-world application scenarios. Evaluation results demonstrate that AutoKaggle achieves a validation submission rate of 0.85 and a comprehensive score of 0.82 in typical data science pipelines, fully proving its effectiveness and practicality in handling complex data science tasks.