研究人机协作中协同结构如何影响团队表现。
Searching for Synergy in Shared Workspace Human-AI Collaboration
- 通过模拟共享工作空间，测试不同协作结构对团队的影响。
- 无协调结构时，增加成员反而降低性能；有结构时三人群体表现最优。
- 引入协同支架可提升效率，适合需分工与责任明确的协作场景。
自动化人工智能代理能力日益增强，但许多科学和专业任务仍需人类判断与情境知识。我们使用基于DiscoveryBench任务的协作健身房（Collaborative Gym）环境，以模拟共享工作空间的人机团队为受控实验平台，考察协作结构如何影响团队行为。在1,482次实验会话中，我们改变团队构成与协作结构。结果发现，在缺乏协调结构的情况下，增加合作者反而会降低性能。随后我们评估了一种协同支架策略，结合共享群体记忆与模拟人类在环（HITL）门控机制，即部分关键操作需由指定模拟成员批准。该支架显著提升性能，尤其在三人团队中效果最明显，表现出更清晰的责任信号和更优的专业技能导向。总体表明，协调结构是决定可用能力能否转化为团队成果的核心因素。
原文摘要 · Abstract (English)
Automated AI agents are increasingly capable, yet many scientific and professional tasks require human judgment and contextual expertise. We use simulated shared-workspace human-AI teams as a controlled testbed for studying how collaboration structure shapes team behavior. Using the Collaborative Gym environment with tasks from DiscoveryBench, we vary team compositions and collaboration structures across 1,482 sessions. We find that adding additional collaborators can lower performance when coordination structure is absent. We then evaluate collaboration scaffolding that combines shared group memory with simulated human-in-the-loop (HITL) gates, where selected actions require approval from a designated simulated participant. This scaffolding improves performance, most clearly in three-person teams, with clearer responsibility signals and stronger routing of expertise to team actions. Overall, our results suggest that coordination structure is central to whether available capability improves team outcomes.
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。