Research on the Application of Generative AI in Immersive Tasks for RPG Games
Main Article Content
Keywords
generative AI, RPG games, immersive tasks
Abstract
In recent years, generative artificial intelligence has developed rapidly, supported by improvements in computing resources, data availability, and model architecture design. The introduction of the Transformer architecture in 2017 provided a key technical basis for later large-scale language models. The release of ChatGPT in 2022 further increased the visibility and adoption of generative AI systems, contributing to their wider application beyond research settings. At present, research in this area has increasingly involved multimodal models and more efficient deployment strategies. In the field of role-playing games (RPGs), many existing task systems are still based on pre-designed scripts, with relatively fixed task structures, limited narrative variation, and constrained interaction patterns between non-player characters (NPCs). These characteristics limit the flexibility of gameplay experience to some extent and make it difficult to fully support diverse player interactions. This paper reviews studies on generative AI applications in RPGs since 2020, focusing on three aspects: narrative generation, dynamic task design, and NPC dialogue systems. It further summarizes current research developments, discusses issues such as content controllability, experience consistency, and computational cost, and outlines several research directions, including multimodal task modeling and personalization mechanisms.
References
- [1] Värtinen, S., Hämäläinen, P., & Guckelsberger, C. (2024). Generating role-playing game quests with GPT language models. IEEE Transactions on Games, 16(1), 127-139. https://doi.org/10.1109/TG.2022.3228480.
- [2] Wang, Y., & Qian, S. F. (2026). Research on the design of children's popular science games based on flow theory. Industrial Design, (04), 61-65. https://doi.org/10.26920/j.cnki.231516cn.2026.04.039.
- [3] Zhang, M. (2023). From game to tourism: A study on the mechanism of influence on tourism intention from the perspective of narrative transportation theory (Doctoral dissertation, Sichuan Agricultural University). https://doi.org/10.27345/d.cnki.gsnyu.2023.001236.
- [4] Wu, L., Wang, Y. H., & Wu, B. (2026). The formation mechanism of tourists’ presence in digital immersive scenarios: A case study of Yangzhou Grand Canal Museum of China. Journal of Central South University of Forestry & Technology (Social Sciences), 20(02), 72-83. https://doi.org/10.14067/j.cnki.1673-9272.2026.02.006.
- [5] Wu, R. N. (2025). Wandering in the “gaps”: An exploration of immersion in RPG games. Contemporary Animation, (04), 109-114.
- [6] Liu, C. X., Wang, M., Yan, S. M., et al. (2026). Unpaired image dehazing algorithm based on memory mechanism and frequency domain learning. Journal of Computer-Aided Design & Computer Graphics, 1-12. https://link.cnki.net/urlid/11.2925.TP.20260227.1406.002.
- [7] Li, J. S., Li, R., & Deng, L. (2026). An automatic extension method of fault tree based on large language model prompt engineering. Computer Applications, 1-7. https://link.cnki.net/urlid/51.1307.TP.20260324.1359.005.
- [8] Liu, H. R., Miao, R. S., & Ye, C. C. (2025). Emergency management question-answering method driven by RAG and fine-tuning of large language models. Smart Computer and Applications, 15(12), 164-170. https://doi.org/10.20169/j.issn.2095-2163.25092801.
- [9] Schlünder, B., & Klabunde, R. (2013). Greetings generation in video role playing games. In Proceedings of the 14th European Workshop on Natural Language Generation (pp. 167–171). Association for Computational Linguistics.
- [10] Pal, P., et al. (2024). Scalable GaN-HEMT model for X-band RF applications. In 2024 8th IEEE Electron Devices Technology & Manufacturing Conference (EDTM) (pp. 1-3). IEEE. https://doi.org/10.1109/EDTM58488.2024.10512345.
- [11] Colinsky, C. (2026). Lunar Command: The GRAG architecture - A white paper on hybrid generative narrative systems. Lunar Command.
- [12] Ashby, T., Webb, B. K., Knapp, G., Searle, J., & Fulda, N. (2023). Personalized quest and dialogue generation in role-playing games: A knowledge graph- and language model-based approach. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI '23) (Article 290, pp. 1–20). Association for Computing Machinery. https://doi.org/10.1145/3544548.3581441.
- [13] Al-Nassar, S., Schaap, A., Van Der Zwart, M., Preuss, M., & Gómez-Maureira, M. A. (2023). QuestVille: Procedural quest generation using NLP models. In Proceedings of the 18th International Conference on the Foundations of Digital Games (FDG '23) (Article 50, pp. 1–4). Association for Computing Machinery. https://doi.org/10.1145/3582437.3587188.
- [14] Chen, D., Zhu, C. K., Sun, Y. Y., et al. (2023). Translation and reliability and validity test of the Clinical Simulation Learning Immersion Scale. Journal of Nursing Science, 38(04), 12-15.
- [15] He, Y. C., Fan, Y. T., & Gao, X. D. (2026). Exploration of the path of college students’ digital sports flow experience to alleviate social anxiety: Based on the perspective of technology immersion and anonymity regulation scenarios. Digital Sports Research, (01), 188-199.
- [16] Ammanabrolu, P., Broniec, W., Mueller, A., Paul, J., & Riedl, M. (2019). Toward automated quest generation in text-adventure games. In Proceedings of the 4th Workshop on Computational Creativity in Language Generation (pp. 1–12). Association for Computational Linguistics.
- [17] van Stegeren, J., & Myśliwiec, J. (2021). Fine-tuning GPT-2 on annotated RPG quests for NPC dialogue generation. In Proceedings of the 16th International Conference on the Foundations of Digital Games (FDG '21) (Article 2, pp. 1–8). Association for Computing Machinery. https://doi.org/10.1145/3472538.3472595.
- [18] Li, L. (2025). Research on safety detection of network audiovisual content based on AI technology. Audio Engineering, 49(06), 94-96+115. https://doi.org/10.16311/j.audioe.2025.06.030.
- [19] Sun, H. Y., Liu, Y. Jun., Yu, L. N., et al. (2025). Unknown intent recognition method based on large model in-context learning. Cybersecurity and Data Governance, 44(11), 38-44. https://doi.org/10.19358/j.issn.2097-1788.2025.11.007.
- [20] Xia, B., Hu, M. L., Yuan, T., et al. (2026). A review of multi-agent collaborative workflows. Software Guide, 25(03), 1-8.
Article Sidebar
This work is licensed under a Creative Commons Attribution 4.0 International License.