Data Science tasks are multifaceted, dynamic, and often domain-specific. Existing LLM-based approaches largely concentrate on isolated phases, neglecting the interdependent nature of many data science tasks and limiting their capacity for comprehensive end-to-end support. We propose DatawiseAgent, a notebook-centric LLM agent framework that unifies interactions among user, agent and the computational environment through markdown and executable code cells, supporting flexible and adaptive automated data science. Built on a Finite State Transducer(FST), DatawiseAgent orchestrates four stages, including DSF-like planning, incremental execution, self-debugging, and post-filtering. Specifically, the DFS-like planning stage systematically explores the solution space, while incremental execution harnesses real-time feedback and accommodates LLM's limited capabilities to progressively complete tasks. The self-debugging and post-filtering modules further enhance reliability by diagnosing and correcting errors and pruning extraneous information. Extensive experiments on diverse tasks, including data analysis, visualization, and data modeling, show that DatawiseAgent consistently outperforms or matches state-of-the-art methods across multiple model settings. These results highlight its potential to generalize across data science scenarios and lay the groundwork for more efficient, fully automated workflows.

该研究解决了数据科学任务中现有大模型方法未能合理支持相互关联的任务阶段的问题。研究提出了一种新的笔记本中心大模型代理框架DatawiseAgent，能够通过markdown和可执行代码单元优化用户、代理与计算环境之间的互动，显著提升自动化数据科学的灵活性和适应性。实验表明，该框架在多种数据科学任务中表现优异，具备广泛的应用潜力。

数据智慧代理：用于自动数据科学的笔记本中心大模型代理框架