发表机构
Purdue University; Microsoft Research（普渡大学; 微软研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出交互式元智能体MUSE，通过重构执行轨迹、支持上下文交互与混合意图操控，提升用户对大语言模型驱动的数据科学系统的理解与控制，经15人被试间研究验证可提高任务效率与用户信心。
AI 中文摘要
大型语言模型的最新进展催生了一类新型智能体驱动的数据科学系统，用户可通过自然语言完成复杂的数据科学工作流。尽管这些系统能大幅减少手动工作量，但当出现故障或意外输出时，诊断其行为并操控推理过程仍十分困难。本文提出MUSE，一种交互式元智能体，通过三方面提升用户对智能体驱动的数据科学系统的理解与控制：其一，将底层执行轨迹动态重构为多个语义层级，支持从高层概览到底层实现细节的导航；其二，允许用户在上下文中引用特定工作流步骤，提出有依据的问题、提供反馈并修正有问题的步骤，无需手动定位相关执行历史；其三，支持混合意图操控，通过呈现可疑步骤供检查、搭建修复流程，并将用户的修复意图转化为底层智能体的上下文指令。在一项被试间研究（样本量n=15）中，MUSE提升了任务效率，增强了用户对理解和操控智能体驱动的数据科学工作流的信心。
英文摘要
Recent advances in large language models have enabled a new class of agentic data science systems that allow users to complete complex data science workflows through natural language. Although these systems can significantly reduce manual effort, it remains difficult to diagnose their behavior and steer the reasoning process when failures or unexpected outputs occur. We present MUSE, an interactive meta-agent that enhances user understanding and control of agentic data science systems by (1) dynamically restructuring low-level execution traces into multiple semantic levels that support navigation from high-level overviews to low-level implementation details; (2) enabling users to reference specific workflow steps in context to ask grounded questions, provide feedback, and revise problematic steps without manually locating relevant execution history; and (3) supporting mixed-initiative steering by surfacing suspicious steps for inspection, scaffolding the repair process, and translating user repair intent into contextualized instructions for the underlying agent. In a between-subjects study (n = 15), MUSE improved task efficiency and increased users' confidence in understanding and steering agentic data science workflows.
CommentsTo appear in the 39th Annual ACM Symposium on User Interface Software and Technology (UIST '26), November 2-5, 2026, Detroit, MI, USA
