发表机构
State Key Lab of CAD&CG, Zhejiang University; Yonsei University; School of Software Technology, Zhejiang University（浙江大学CAD&CG国家重点实验室; 延世大学; 浙江大学软件学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对长时间智能体数据分析的传统界面无法满足可观测性与可引导性需求，本文提出交互式系统AdaLens，结合故事情节表示与引导交互，经案例及用户研究验证其能有效支持分析师监控与引导此类分析。
AI 中文摘要
大型语言模型正推动数据科学向越来越自主的智能体工作流发展，近期系统已支持多步骤及长时间运行的分析。随着这些工作流愈发自主，传统界面已无法满足两项关键需求：一是可观测性，用于理解智能体不断演变的推理与证据；二是可引导性，用于在执行过程中重定向低价值方向或深化有前景的方向。现有交互方法虽提升了过程可见性并开放了干预点，但主要针对离散的逐轮交互设计，而非长时间智能体分析的并行分支与演变决策结构。我们将此需求视为长时间智能体数据分析中的交互式监督，提出AdaLens，这是一款用于监控和引导运行中任务的交互式系统。AdaLens结合了基于故事情节的表示，该表示统一了分析计划、执行进度、中间发现及数据列参与情况，以及基于这些分析元素的引导交互，用于方向指导和执行控制。我们通过两个案例研究和一项用户研究对AdaLens进行评估，检验其如何支持分析师监控和引导长时间运行的智能体数据分析。
英文摘要
Large language models are pushing data science toward increasingly autonomous and agentic workflows, with recent systems already supporting multi-step and long-running analyses. As these workflows become more autonomous, conventional interfaces no longer provide adequate support for two critical requirements: observability for understanding an agent's evolving reasoning and evidence, and steerability for redirecting low-value directions or deepening promising ones during execution. Existing interactive approaches improve process visibility and open intervention points, but they remain largely designed for discrete, turn-by-turn exchanges rather than the parallel branches and evolving decision structures of long-running agentic analysis. We study this need as interactive oversight in long-running agentic data analysis and present AdaLens, an interactive system for monitoring and steering ongoing runs. AdaLens combines a storyline-based representation that unifies analytical plans, execution progress, intermediate findings, and data-column involvement with steering interactions grounded in these analytical elements for directional guidance and execution control. We evaluate AdaLens through two case studies and a user study, examining how it supports analysts in monitoring and steering long-running agentic data analysis.
