Collaborative problem-solving under time pressure is common but difficult, as teams must generate ideas quickly, coordinate actions, and track progress. Generative AI offers new opportunities to assist, but we know little about how proactive agents affect the dynamics of real-time, co-located teamwork. We studied two forms of proactive support in digital escape rooms: a facilitator agent that offered summaries and group structures, and a peer agent that proposed ideas and answered queries. In a within-subjects study with 24 participants, we compared group performance and processes across three conditions: no AI, peer, and facilitator. Results show that the peer agent occasionally enhanced problem-solving by offering timely hints and memory support; however, it also disrupted flow, increased workload, and created over-reliance. In comparison, the facilitator agent provided light scaffolding but had a limited impact on outcomes. We provide design considerations for proactive generative AI agents based on our findings.

翻译：在时间压力下进行协作问题解决是常见但困难的任务，因为团队需要快速生成想法、协调行动并跟踪进度。生成式AI为协助此类任务提供了新的机遇，但我们对主动代理如何影响实时、共址团队协作的动态过程知之甚少。本研究在数字密室逃脱环境中考察了两种主动支持形式：提供总结与团队结构建议的协调者代理，以及提出想法并回答查询的同伴代理。我们通过一项包含24名参与者的被试内实验，比较了三种条件（无AI、同伴代理、协调者代理）下的团队绩效与协作过程。结果表明，同伴代理通过提供及时提示和记忆支持，偶尔能促进问题解决；然而，它也会打断工作流、增加认知负荷并导致过度依赖。相比之下，协调者代理虽能提供轻度支架支持，但对任务结果的影响有限。基于研究发现，我们为主动生成式AI代理的设计提出了若干考量。