AI summaryⓘ
The authors studied how people feel about using AI agents to talk for them on dating platforms, focusing not just on sending messages through agents but also on receiving them from others. They found that people are much more willing to let their own agent send messages than to accept messages sent by someone else's agent. Using surveys from two languages, the authors showed these two attitudes are related but distinct, with notable differences by gender and interaction direction. They tested different design ideas and found that requiring both sides to agree to use agents cuts down interactions a lot, while smartly matching agent messages to people willing to receive them greatly boosts engagement. The study provides insights for designing AI-powered dating services that respect users’ comfort and preferences.
LLM agentsagent-mediated communicationlatent-variable measurement modelgraded response modelagent receptivitydelegation asymmetryrandom-pairing counterfactualreceptivity-aware matchmakinggender-directional imbalance
Authors
Daria Leshchikova, Valentina V. Kuskova, Dmitry Zaytsev, Valerii Klimov
Abstract
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.