Right-Sizing Communication and Recommendation Set Size in AI-Assisted Search

A new study models the interaction between users and AI recommendation systems, finding that the optimal number of product suggestions depends on the cost of user communication versus search effort. Researchers analyzed how an AI assistant, acting as a Bayesian agent, should balance the precision of a user's preference message against the size of the recommendation set to maximize expected utility. The results reveal that under certain conditions, the most efficient policy requires jointly optimizing both communication and recommendation set size, while under others, it favors whichever cost is lower.

arXiv:2605.23944v1 Announce Type: new Abstract: We model the interaction between a user and an AI driven recommendation system. The user initiates the process by conveying preference information through a costly and noisy message. The AI assistant, acting as a Bayesian agent, interprets the user's message to form a posterior belief about their true preferences and make product recommendations. In particular, it determines how many recommendations to present so as to maximize the user's expected utility from their final choice, while accounting for the search cost induced by the size of the recommendation set. We use mutual information based cost functions to model the two distinct costs incurred by the user during the interaction: i a communication cost, which increases with the precision of their preference message, and ii a search cost, which increases with the size of the recommendation set provided by the AI assistant. We study products and preferences which live in d dimensional space, and ask how the user's expected payoff can be maximized. For large d, we characterize how optimal message precision and recommendation set size depend on the cost parameters, under two distinct distributions from which recommendations can be sampled from the product universe: i Bayes' posterior belief, and ii an optimized tilted distribution. Under the posterior sampling scheme i , we identify a hybrid regime, in which an efficient interaction policy requires jointly optimizing the amount of information in bits conveyed by the user and the number of recommendations provided by the AI assistant. In the tilted sampling scheme ii , our results show that the optimal interaction policy uses only one of communication and search, favoring whichever of them is less costly.