Design of Generative AI Game NPCs Based on Human-Computer Interaction
DOI:
https://doi.org/10.54097/hy3mx976Keywords:
Generative Artificial Intelligence, Large Language Models, Non-player Characters, Human-computer Interaction, Game Design, Iterative EvaluationAbstract
The generative artificial intelligence (Generative AI) and the large language models (LLMs) are developing at a very fast pace, which has led to the fundamental change in the way of interaction with the non-player characters (NPCs) in the games. The conventional NPCs have no dynamic reaction mechanisms or long-term memory, and therefore they cannot be used to satisfy the requirements of the authenticity and immersion in the modern open-world games as it is not possible to use them effectively. In the past few years, the topic of designing an NPC based on LLMs has been discussed in detail by many researchers within the academic world including topics like personality consistency, dialogue creation, contextual adjustment, etc. Most current works however deal with the technical aspects and do not provide systematic description of how to evaluate and design using human-computer interaction (HCI). The paper presents and applies the generative AI NPC design paradigm that uses the LLMs through the lens of HCI. This can be done through the introduction of such methods as contextual design, low-fidelity. The design-evaluation-redesign process, which is based on the prototyping, think-aloud and heuristic evaluation of the possibilities of AI NPCs in the dynamic dialogue, contextual adaptation and behavior prediction, will be developed as a series of iterative steps. The system has been prototyped with an open-domain dialogue, with a React front-end and an LLM API that supports contextual memory. The mixed-methods study approach to the experimental research includes the quantitative analysis of the immersion of the players and the efficiency of their task performance and qualitative measurement of the user interaction. There are expected results of having a prototype system of an interactive AI NPC, a collection of guidelines to interact with generative AI NPCs, and a set of experimental and assessment toolkits to conduct research at the intersection of HCI-AI. This paper gives theoretical basis and practical directions to the application of the concept of generative AI to game interaction.
Downloads
References
[1] Yannakakis, G. N., & Togelius, J. (2018). Artificial intelligence and games. Springer. https://doi.org/10.1007/978-3-319-63519-4. DOI: https://doi.org/10.1007/978-3-319-63519-4
[2] Klinkert, J., Clark, C., & Buongiorno, S. (2025). Personality-consistent NPCs using large language models. arXiv preprint, arXiv:2402.14879. https://doi.org/10.48550/arXiv.2402.14879.
[3] Rabin, S. (Ed.). (2019). Game AI Pro 360: Gather the wisdom of the world's best AI programmers. CRC Press. DOI: https://doi.org/10.1201/9780429055058
[4] Lankoski, P., & Björk, S. (Eds.). (2015). Game design research: An introduction to theory & practice. ETC Press, Carnegie Mellon University.
[5] Yang, D., et al. (2024). GPT for games: An updated scoping review (2020–2024). arXiv preprint, arXiv:2411.00308. https: // doi. org/10.48550/arXiv.2411.00308.
[6] Rimer, E., Ploug, R., Petersen, A. K. S., & Scirea, M. (2025). Talking to NPCs: Three LLM-driven approaches to dynamic RPG dialogue. In 2025 IEEE Conference on Games (CoG). IEEE Press. https://doi.org/10. 1109/ CoG64752. 2025. 1111 4413. DOI: https://doi.org/10.1109/CoG64752.2025.11114413
[7] Ploug, R., Rimer, E., Skov Petersen, A. K., & Scirea, M. (2025). Open-ended NPC dialogue favors casual players: A pilot comparison of three LLM-driven dialogue systems. In Proceedings of the IEEE 2025 Conference on Games (CoG). IEEE Press. https://doi.org/ 10.1109/ CoG64752. 2025.11114 150. DOI: https://doi.org/10.1109/CoG64752.2025.11114150
[8] Feng, Y., Miao, Y., & Zhou, Y. (2025). Research on the humanization design of game NPCs and user experience optimization based on large language models. In Proceedings of the 2025 3rd International Conference on Image, Algorithms, and Artificial Intelligence (ICIAAI 2025) (pp. 789–796). Atlantis Press. https://doi.org/10.2991/978-94-6463-823-3_94. DOI: https://doi.org/10.2991/978-94-6463-823-3_94
[9] Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Wang, M., & Wang, H. (2024). Retrieval-augmented generation for large language models: A survey. arXiv preprint, arXiv:2312.10997. https://doi.org/10.48550/arXiv.2312.10997.
[10] Radež, G., & Bohak, C. (2026). Empowering NPC dialogue with environmental context using LLMs and panoramic images. arXiv preprint, arXiv:2604.19192. https://doi.org/10. 48550/ arXiv. 2604.19192.
[11] Braas, M., & Esterle, L. (2025). Fixed-persona SLMs with modular memory: Scalable NPC dialogue on consumer hardware. arXiv preprint, arXiv:2511.10277. https://doi.org/10. 48550/ arXiv.2511.10277.
[12] Du, L., & Jia, T. X. (2024). Generative artificial intelligence and the innovation of video game production mechanisms. Art Research, (2), 58–66.
[13] Li, D. F. (2024). Digital maze and wax wings — Prospects and challenges of generative intelligent NPCs in video games. Journal of Beijing Film Academy, (12), 39–48.
[14] Wu, Z., Chen, Z., Zhu, D., Mousas, C., & Kao, D. (2025). A systematic review of generative AI on game character creation: Applications, challenges, and future trends. IEEE Transactions on Games. https://doi.org/10.1109/TG.2025.3564869. DOI: https://doi.org/10.1109/TG.2025.3564869
[15] Ternar, D. A., Denisova, A., Cunha, J. M., Kultima, A., & Guckelsberger, C. (2025). Generative AI in game development: A qualitative research synthesis. In Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems. https://doi.org/10.1145/3613905.3642142. DOI: https://doi.org/10.1145/3772318.3791206
[16] Shido, T. (2025). Examination of model efficiency and its application in the game field for Japanese large-scale language models. In Proceedings of the 23rd International Conference of Asia Digital Art and Design Association. Tokyo Metropolitan University.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Frontiers in Computing and Intelligent Systems
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
