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 2603.02050cs.HCcs.AI
收藏

何时交接,何时协作:通过并发交互扩展人机协同创作

"When to Hand Off, When to Work Together": Understanding Concurrent Human-Agent Interaction in Shared Co-Creative Workspaces

School of Computing, KAIST(韩国科学技术院计算学院);Computer Science and Engineering, University of Michigan(密歇根大学计算机科学与工程系)

Kihoon Son, Hyewon Lee, DaEun Choi, Yoonsu Kim, Tae Soo Kim, Yoonjoo Lee, John Joon Young Chung, HyunJoon Jung, Juho Kim

AI总结:

研究探讨人机协同创作中并发交互的模式与能力需求,提出决策模型和标注数据集,揭示并发交互提升委托效果的核心作用。

摘要:

随着智能体进入共享工作空间,其执行变得可见,人机协作从顺序委托转向并发共创。这引发新的协调问题:何种交互模式出现,何种智能体能力支持这些模式?研究1(N=10)发现过程可见性自然促使并发干预,但暴露关键能力缺口:智能体缺乏协同上下文感知能力,无法区分用户反馈与独立并行工作。这促使设计探针CLEO,通过解读并发用户行为作为反馈或独立工作并调整执行。研究2(N=10)分析214次交互,识别五种行动模式和十个代码,以及六个触发因素和四个促成因素,解释何时及为何用户切换协作模式。并发交互出现在31.8%的回合中。我们提出决策模型、设计启示和标注数据集,将并发交互定位为使委托更有效的关键因素。

英文摘要:

Shared co-creative workspaces allow users to contribute while agents execute. Yet how users adjust their participation as their work and the agent's execution shape one another remains less understood. We conducted two design probe studies with professional designers. In Study 1 (N=10), participants identified opportunities to contribute by observing the agent's progress, but avoided intervention when the agent misinterpreted their edits. Therefore, we developed CLEO, a second probe that tracks user actions and selectively updates its plan. In Study 2 (N=12), we analyzed 255 interaction turns and stimulated recall interviews, identifying five action categories, ten codes, six triggers, and four enabling factors. Participants engaged in concurrent interaction during 33.73% of turns, expressing newly recognized design ideas or preferences through edits and changing the division of work by completing pending subtasks or independently developing copies of unfinished outputs. We present a decision model and five design implications for concurrent human-agent collaboration.

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。

↑