@inproceedings{you-etal-2025-datawiseagent,
    title = "{D}atawise{A}gent: A Notebook-Centric {LLM} Agent Framework for Adaptive and Robust Data Science Automation",
    author = "You, Ziming  and
      Zhang, Yumiao  and
      Xu, Dexuan  and
      Lou, Yiwei  and
      Yan, Yandong  and
      Wang, Wei  and
      Zhang, Huamin  and
      Huang, Yu",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.58/",
    pages = "1099--1123",
    ISBN = "979-8-89176-332-6",
    abstract = "Existing large language model (LLM) agents for automating data science show promise, but they remain constrained by narrow task scopes, limited generalization across tasks and models, and over-reliance on state-of-the-art (SOTA) LLMs. We introduce DatawiseAgent, a notebook-centric LLM agent framework for adaptive and robust data science automation. Inspired by how human data scientists work in computational notebooks, DatawiseAgent introduces a unified interaction representation and a multi-stage architecture based on finite-state transducers (FSTs). This design enables flexible long-horizon planning, progressive solution development, and robust recovery from execution failures. Extensive experiments across diverse data science scenarios and models show that DatawiseAgent consistently achieves SOTA performance by surpassing strong baselines such as AutoGen and TaskWeaver, demonstrating superior effectiveness and adaptability. Further evaluations reveal graceful performance degradation under weaker or smaller models, underscoring the robustness and scalability."
}