智能体推荐系统中的委托不对称性：在线约会中的双边接受度测量

中文摘要 AI 辅助

以用户名义进行对话的自主大语言模型（LLM）智能体是匹配平台的新兴设计模式，但其可行性取决于一个很少被研究的条件：用户不仅必须接受将对话委托给智能体，还必须接受来自他人的智能体中介通信。我们通过对某主流约会平台活跃用户的两项大规模调查研究该条件（关于生成式资料特征的N=2894人；关于自主对话智能体的N=2617人，以两种语言开展）。我们基于带潜在回归的分级反应模型开发了智能体接受度的潜在变量测量模型，并通过模型比较表明，发送智能体通信的意愿与接收智能体通信的意愿是不同的构念：高度相关（rho=0.92）但可分离（Delta BIC=52），且跨语言存在部分测量不变性。该模型量化了系统性委托不对称性：部署自身智能体所需的接受度低得多（阈值-0.38），而对接对方智能体则需更高接受度（+0.32；完全对接需+1.39），且平均部署倾向约为对接倾向的三倍。基于所声明接受度得出的随机配对反事实下，仅4%-13%的定向配对结合了智能体部署与接收方对接，且存在明显的性别方向不平衡。设计反事实量化了杠杆：互惠要求通过排除近三分之二的潜在部署使交互量减半或更多，而基于接收接受度路由智能体联系人则使每次联系人的对接量增至三倍，该提升在保留目标项的样本外验证中依然存在（AUC=0.88，受访者层面交叉验证下的3.1x四分位提升）。我们讨论了对智能体推荐设计的启示，包括披露、选择加入机制和感知接受度的匹配。

英文摘要

Autonomous LLM agents that converse on a user's behalf are an emerging design pattern in matching platforms, yet their viability depends on a condition rarely examined: users must accept not only delegating conversation to an agent, but also receiving agent-mediated communication from others. We study this condition using two large-scale surveys of active users of a major dating platform (N=2,894 on generative profile features; N=2,617 on autonomous conversational agents, fielded in two languages). We develop a latent-variable measurement model of agent receptivity based on graded response models with latent regression, and show via model comparison that willingness to send and willingness to receive agent communication are distinct constructs: highly correlated (rho=0.92) but separable (Delta BIC=52), with partial measurement invariance across languages. The model quantifies a systematic delegation asymmetry: deploying one's own agent requires far lower receptivity (threshold -0.38) than engaging a counterpart's agent (+0.32; full engagement +1.39), and mean deployment propensity exceeds engagement propensity roughly threefold. Under a random-pairing counterfactual derived from stated receptivity, only 4-13% of directed dyads combine agent deployment with receiver engagement, with a pronounced gender-directional imbalance. Design counterfactuals quantify the levers: a reciprocity requirement cuts interaction volume by half or more by excluding nearly two-thirds of would-be deployment, while routing agent contacts on receive receptivity triples per-contact engagement, a lift that survives out-of-sample validation with the target item held out (AUC 0.88, 3.1x quartile lift under respondent-level cross-validation). We discuss implications for agentic recommender design, including disclosure, opt-in mechanics, and receptivity-aware matchmaking.

发表机构

• Fleamily, Inc.（弗利米利公司）
• Lucy Family Institute for Data & Society（露西数据与社会研究所）
• University of Notre Dame（圣母大学）

机构由 AI 辅助整理，请以论文原文为准。