arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.15569cs.HC
收藏

你在做什么?代理LLM车载助手在多步骤处理中的中间反馈影响

What Are You Doing? Effects of Intermediate Feedback from Agentic LLM In-Car Assistants During Multi-Step Processing

BMW Group Research and Technology(宝马集团研究与技术);Augsburg University(奥格斯堡大学);LMU Munich(慕尼黑大学)

Johannes Kirmayr, Raphael Wennmacher, Khanh Huynh, Lukas Stappen, Elisabeth André, Florian Alt

AI总结:

研究探讨了代理式LLM车载助手在多步骤处理中中间反馈对用户体验的影响,发现中间反馈能提升信任和效率,同时减少任务负荷,提出适应性反馈策略以平衡透明度与效率。

摘要:

代理式AI助手能够自主执行多步骤任务,这在用户体验方面提出了开放性问题:在长时间操作中,此类系统应如何沟通进度和推理,尤其是在注意力关键的上下文如驾驶时?我们通过一个受控的混合方法研究(N=45)来探讨代理式LLM车载助手的反馈时机和详尽程度,比较计划步骤和中间结果反馈与静默操作仅最终响应的对比。使用车载语音助手的双任务范式,我们发现中间反馈显著提高了感知速度、信任度和用户体验,同时减少了任务负荷——这些效果在不同任务复杂性和交互上下文中都保持一致。进一步的访谈揭示了用户的偏好:在建立信任时需要高初始透明度,随后逐步减少详尽程度,随着系统证明可靠而调整,根据任务重要性和情境上下文进行调整。我们将实证发现转化为代理助手反馈时机和详尽程度的设计启示,平衡透明度和效率。

英文摘要:

Agentic AI assistants that autonomously perform multi-step tasks raise open questions for user experience: how should such systems communicate progress and reasoning during extended operations, especially in attention-critical contexts such as driving? We investigate feedback timing and verbosity from agentic LLM-based in-car assistants through a controlled, mixed-methods study (N=45) comparing planned steps and intermediate results feedback against silent operation with final-only response. Using a dual-task paradigm with an in-car voice assistant, we found that intermediate feedback significantly improved perceived speed, trust, and user experience while reducing task load - effects that held across varying task complexities and interaction contexts. Interviews further revealed user preferences for an adaptive approach: high initial transparency to establish trust, followed by progressively reducing verbosity as systems prove reliable, with adjustments based on task stakes and situational context. We translate our empirical findings into design implications for feedback timing and verbosity in agentic assistants, balancing transparency and efficiency.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑