AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions

Ziming Li, Qianbo Zang, dma2077, Jiawei Guo, TY.Zheng, minghao, Xinyao Niu, Yue Wang, Jian Yang, Jiaheng Liu, Wanjun Zhong, Zhou, Wenhao Huang, Ge Zhang

AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions: 40 upvotes on Hugging Face Daily Papers, #2 of 15 papers on 2024-10-30. Day-by-day upvote history.

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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.