研究用户对代理聊天的接受度差异，发现发与收不对等，影响约会平台设计。
Delegation Asymmetry in Agentic Recommender Systems: Measuring Two-Sided Receptivity in Online Dating
- 用潜变量模型测量用户发送和接收代理消息的意愿，发现二者虽相关但可区分。
- 自用代理门槛低（阈值-0.38），对方用代理则需更高接受度（+0.32）。
- 若双方都愿用代理，实际配对仅4%-13%，性别方向差异明显。
在主流约会平台的两项大规模调查中（生成资料功能N=2,894；自主对话代理N=2,617，分两种语言），我们研究了用户对代理沟通的双向接受度。通过基于等级响应模型的潜变量测量模型，发现发送与接收代理通信的意愿高度相关（rho=0.92）但可分离（Delta BIC=52），跨语言部分测量不变。模型揭示系统性委托不对称：使用自身代理所需接受度（阈值-0.38）远低于接收他人代理（+0.32；完全参与+1.39），平均部署倾向是参与倾向的三倍左右。基于声明接受度的随机配对反事实显示，仅有4%-13%的配对同时具备代理部署与接收意愿，且存在显著性别方向失衡。设计反事实分析表明：互惠要求使互动量减半以上，排除近三分之二潜在部署者；按接收接受度路由代理消息可使每条消息参与度提升三倍，该效果在样本外验证中稳定（AUC 0.88，受访者交叉验证下3.1倍四分位提升）。讨论了对代理推荐系统设计的启示，包括披露机制、选择方式及感知接受度导向匹配。
原文摘要 · Abstract (English)
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.
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。