对比自动与引导式助手，发现后者更利于用户学习和掌控复杂任务。
Do It For Me vs. Do It With Me: Investigating User Perceptions of Different Paradigms of Automation in Copilots for Feature-Rich Software
- 设计引导式助手，分步可视化指导用户完成任务
- 引导式助手在创意任务中显著提升学习效率与控制感
- 适合希望主动学习的用户，尤其擅长探索性工作
基于大语言模型的应用内助手（即协作智能体）可自动化软件操作，但用户常偏好通过实践学习，这引发了关于最佳自动化程度的疑问。我们设计并实现了完全自动化（AutoCopilot）与半自动化（GuidedCopilot）两种模式：后者自动化简单步骤，同时提供分步视觉引导。在20名用户的实验中，面对数据分析与视觉设计任务，GuidedCopilot在用户控制力、软件实用性及可学性方面优于AutoCopilot，尤其在探索性和创造性任务中表现更佳；而AutoCopilot在简单视觉任务中节省更多时间。后续10人设计探索进一步优化了GuidedCopilot，加入任务与状态感知功能，如上下文预览片段与自适应提示。研究强调，用户控制力与定制化引导对提升生产力、支持多技能水平用户、促进深度软件参与至关重要。
原文摘要 · Abstract (English)
Large Language Model (LLM)-based in-application assistants, or copilots, can automate software tasks, but users often prefer learning by doing, raising questions about the optimal level of automation for an effective user experience. We investigated two automation paradigms by designing and implementing a fully automated copilot (AutoCopilot) and a semi-automated copilot (GuidedCopilot) that automates trivial steps while offering step-by-step visual guidance. In a user study (N=20) across data analysis and visual design tasks, GuidedCopilot outperformed AutoCopilot in user control, software utility, and learnability, especially for exploratory and creative tasks, while AutoCopilot saved time for simpler visual tasks. A follow-up design exploration (N=10) enhanced GuidedCopilot with task-and state-aware features, including in-context preview clips and adaptive instructions. Our findings highlight the critical role of user control and tailored guidance in designing the next generation of copilots that enhance productivity, support diverse skill levels, and foster deeper software engagement.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。