arXiv cs.AI· Jiadong Bai, Yicong Huang, Chen Li·· 11 小时前AI 评分38
BobFlow：用数据流实现人机协作数据科学
BobFlow: Towards Human-Agent Collaborative Data Science Using Dataflows
AI 导读
BobFlow 将数据流抽象与 ReAct 范式结合，让智能体迭代构建并执行数据流完成数据科学任务，分析师可检查分析过程并给出反馈。在专有与开源权重 LLM 上的实验显示，准确率最高提升 18.6 分，推理成本仅为基于脚本的 ReAct 智能体的 1/3 略多。用户研究表明该系统能帮助分析师理解、检查和验证智能体生成的分析。
正文 · 原文
Abstract:Recent advances in large language models (LLMs) have established human-agent collaboration as a promising paradigm for data science. Effective collaboration requires a shared computational abstraction that enables agents to reason about processing logic while allowing human analysts to understand, guide, and refine the analysis. Although scripts written in Python or SQL provide precise control, their syntax and execution details can be difficult for analysts to understand and modify. In this paper, we argue that dataflows are an effective abstraction for human-agent collaboration in data science. We introduce BobFlow, a system that combines the dataflow abstraction with the ReAct paradigm. It enables agents to iteratively construct and execute dataflows for data science tasks while allowing analysts to inspect the analysis and provide feedback. Our user study shows that BobFlow helps analysts understand, inspect, and verify agent-generated analyses. A thorough experimental evaluation across proprietary and open-weight LLMs shows accuracy score gains of up to 18.6 points at just over 1/3 of a script-based ReAct agent's inference cost.
| Subjects: | Databases (cs.DB); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC) |
| Cite as: | arXiv:2611.05761 [cs.DB] |
| (or arXiv:2611.05761v1 [cs.DB] for this version) | |
| https://doi.org/10.48550/arXiv.2611.05761 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jiadong Bai [view email]
[v1]
Wed, 4 Nov 2026 00:02:41 UTC (2,273 KB)
来源：arXiv cs.AI · arxiv.org