AI Teammate Behavior and Player Experience in Cooperative Board Games: A Review
Main Article Content
Keywords
cooperative board games, AI teammates, player experience, human -AI collaboration, behavioral design, literature 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 collaboration. 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, perceived 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.
References
- [1] Perez, L. (2021). Mastering Terra Mystica: Applying self-play to multi-agent cooperative board games. arXiv. https://arxiv.org/abs/2102.10540
- [2] Hu, H., Lerer, A., Hu, B., Foerster, J., & Brown, N. (2022). Generating and adapting to diverse ad hoc partners in Hanabi. IEEE Transactions on Games. Advance online publication. https://www.x- mol.com/paper/1534679146241527808/t
- [3] Palatsi, A. C., Gä chter, S., Kleiman, T., & McElreath, R. (2025). Large language models replicate and predict human cooperation across experiments in game theory. arXiv. https://arxiv.org/abs/2511.04500
- [4] Ma, Y., Lu, C., Lv, K., Hao, J., Liu, T. -Y., & Fu, J. (2023). Fast Peer Adaptation with Context-aware Exploration. Proceedings of the 40th International Conference on Machine Learning (ICML), 2023. https://proceedings.mlr.press/v235/ma24n.html
- [5] Hammond, R., Bou-Ammar, H., & Howley, E. (2024). Symmetry-breaking augmentations for ad hoc teamwork. arXiv. https://arxiv.org/abs/2402.09984
- [6] Kraus, M., Riekenbrauck, R., & Minker, W. (2023). Development of a trust-aware user simulator for statistical proactive dialog modeling in human-AI teams. In Adjunct Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization (pp. 38–43). ACM. https://doi.org/10.1145/3563359.3597403
- [7] Gong, R., Li, J., Zhu, J., Ma, Y., Chen, X., Chen, S., Ma, H., & Xu, H. (2023). MindAgent: Emergent gaming interaction. arXiv. https://arxiv.org/abs/2309.09971
- [8] Sidji, M., Smith, W., & Rogerson, M. J. (2024). Human-AI Collaboration in Cooperative Games: A Study of Playing Codenames with an LLM Assistant. Proceedings of the ACM on Human-Computer Interaction, 8(CHI PLAY), 1-25. https://doi.org/10.1145/3677081
Article Sidebar
This work is licensed under a Creative Commons Attribution 4.0 International License.