arXiv cs.CY· Harang Ju, Sinan Aral·· 12 小时前AI 评分58
AI 智能体协作的现场实验：团队协作、生产力与绩效
Collaborating with AI Agents: Field Experiments on Teamwork, Productivity, and Performance
AI 导读
研究者基于自建平台 Pairit 开展大规模实验，将 2234 名参与者随机分配到人机团队与人际团队，共产出 11024 条广告。结果显示人机团队人均广告产出多 50%、文本质量更高，人际团队图像质量更高，但人机团队输出更同质化；X 上的现场实验获得约 500 万次曝光，文本质量更高提升了点击率与浏览时长，图像质量更高则改善每次点击成本。作者指出任务导向沟通与更多委派是两条关键机制。
正文 · 原文
Abstract:We examined the mechanisms underlying productivity and performance gains from AI agents using a large-scale experiment on Pairit, a platform we developed to study human-AI collaboration. We randomly assigned 2,234 participants to human-human and human-AI teams that produced 11,024 ads. We evaluated the ads using independent human ratings and a field experiment on X which garnered ~5M impressions. We found human-AI teams produced 50% more ads per worker and higher text quality, while human-human teams produced higher image quality, suggesting a jagged frontier of AI agent capability. Human-AI teams also produced more homogeneous outputs (diversity collapse) as their ads were more self-similar. The field experiment revealed higher text quality (produced by human-AI teams) increased click-through rates and view time, while higher image quality (produced by human-human teams) improved cost-per-click rates. Two mechanisms explained these effects: Human-AI collaboration was significantly more task-oriented and displayed more delegation. AI-appropriate work processes, in turn, improved performance in human-AI teams and transcended the jagged frontier: Task-oriented communication produced higher productivity, higher quality ads across all dimensions, and displayed no diversity collapse in their outputs, while human-AI teams with more interpersonal communication were less productive and produced lower quality ads across all dimensions. In contrast, in human-human teams, interpersonal communication improved productivity. Delegation improved text quality in human-AI teams and was positively associated with diversity collapse, creating homogeneous outputs of higher average quality. The results suggest AI agents drive productivity, performance, and output diversity by reshaping teamwork along the jagged frontier of AI capabilities.
| Comments: | 76 pages, 4 figures, 22 tables |
| Subjects: | Computers and Society (cs.CY); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2503.18238 [cs.CY] |
| (or arXiv:2503.18238v4 [cs.CY] for this version) | |
| https://doi.org/10.48550/arXiv.2503.18238 arXiv-issued DOI via DataCite |
Submission history
From: Harang Ju [view email]
[v1]
Sun, 23 Mar 2025 23:20:32 UTC (17,155 KB)
[v2]
Fri, 15 Aug 2025 17:18:44 UTC (4,216 KB)
[v3]
Thu, 5 Feb 2026 00:30:16 UTC (2,083 KB)
[v4]
Thu, 15 Oct 2026 13:52:42 UTC (2,106 KB)
来源：arXiv cs.CY · arxiv.org