AI Teammate Behavior and Player Experience in Cooperative Board Games: A Review

Abstract

Cooperative board games combine strategic problem-solving with communication, shared decision-making, and social interaction. AI teammates can lower barriers for novice players, support solo play, and provide a controlled setting for studying human -AI coll aboration. However, high task performance alone does not guarantee a positive player experience: an effective but opaque agent may reduce players' sense of agency, whereas a socially expressive agent with weak task competence may undermine trust. This review synthesizes research from game AI, human-computer interaction, and multi-agent systems to examine three behavioral dimensions of AI teammates: ability alignment, transparency of intent, and socio-emotional expression. It further discusses trust, perceiv ed control, and social presence as potential psychological mechanisms linking AI behavior to enjoyment, collaboration quality, and continued engagement. The reviewed evidence suggests that successful AI teammates should balance competence, interpretability, adaptability, and social expressiveness rather than maximize win rate alone. Based on this synthesis, the paper proposes an “AI behavior–psychological mechanisms –player experience” framework, summarizes relevant implementation and evaluation methods, and identifies research priorities for more reliable and player-centered AI teammate design.