Non-Playable Characters Based On Large Language Models For Role Playing Games (RPG)

Ade Mulyana; Yudi Wibisono; Ani Anisyah

doi:10.47709/brilliance.v5i2.6779

Non-Playable Characters Based On Large Language Models For Role Playing Games (RPG)

Authors

Ade Mulyana Universitas Pendidikan Indonesia, Indonesia
Yudi Wibisono Universitas Pendidikan Indonesia, Indonesia
Ani Anisyah Universitas Pendidikan Indonesia, Indonesia

DOI:

https://doi.org/10.47709/brilliance.v5i2.6779

Keywords:

Artificial Intelligence, Large Language Model, Non-Playable Character, Retrieval-Augmented Generation, Role-Playing Game

Abstract

Interactive dialogue is a central element in role-playing games (RPG), particularly those that emphasize storytelling and immersion. This study explores the development of a dynamic Non-Playable Character (NPC) system using a Large Language Model (LLM) to simulate responsive conversations in a fictional world. The objective of this research is to design an NPC dialogue system that can maintain contextual consistency with the game’s lore while adapting to player input dynamically. The method used is engineering-based development, involving prompt engineering and a Retrieval-Augmented Generation (RAG) approach to embed narrative context into the LLM prompts. The system is implemented in a 2D RPG titled Kage no Meiyaku: Shinobi no Michi, where players interact with multiple NPCs whose responses evolve based on both pre-defined lore and game progression. Evaluation is conducted using a Likert scale across four dialogue quality dimensions: coherence, emotional engagement, narrative relevance, and persona consistency. The results show that the system generates engaging and contextually accurate responses, with average scores ranging from 4.0 to 4.5. Some limitations are identified, such as occasional misspellings and generic responses in ambiguous inputs. However, the approach demonstrates strong potential for AI-assisted storytelling in games. This research contributes to expanding LLM applications in interactive fiction and opens future work toward feature-rich RPG elements such as transactional systems, branching narratives, and real-time battle interactions.

References

Collins, J., Hirst, W., Tang, W., Luu, C., Smith, P., Watson, A., & Sahandi, R. (2016). EDTree: Emotional dialogue trees for game based training.

Gallotta, R., Todd, G., Zammit, M., Earle, S., Liapis, A., Togelius, J., & Yannakakis, G. N. (2024). Large Language Models and Games: A Survey and Roadmap. 1–19. https://doi.org/10.1109/TG.2024.3461510

Gao, Q., Isaac, S., Way, B., Catharines, S., Emami, A., & Catharines, S. (2023). The Turing Quest?: Can Transformers Make Good NPCs?? 93–103.

Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Wang, M., & Wang, H. (2023). Retrieval-Augmented Generation for Large Language Models: A Survey. 1–21. http://arxiv.org/abs/2312.10997

Jenkins, H. (2004). Game Design as Narrative Architecture. In N. Wardrip-Fruin & P. Harrigan (Eds.), First Person: New Media as Story, Performance, and Game (pp. 118-130). MIT Press.

Jennett, C., Cox, A. L., Cairns, P., Dhoparee, S., Epps, A., Tijs, T., & Walton, A. (2008). Measuring and defining the experience of immersion in games. International Journal of Human-Computer Studies, 66(9), 641–661. https://doi.org/10.1016/j.ijhcs.2008.04.004

Ji, K., Lian, Y., Li, L., Gao, J., Li, W., & Dai, B. (2025). Enhancing Persona Consistency for LLMs’ Role-Playing using Persona-Aware Contrastive Learning. http://arxiv.org/abs/2503.17662

Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., ... & Kiela, D. (2021). Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in Neural Information Processing Systems, 33, 9459–9474. https://papers.nips.cc/paper/2020/file/6b493230205f780e1bc26945df7481e5-Paper.pdf

Mao, Y., Ge, Y., Fan, Y., Xu, W., Mi, Y., Hu, Z., & Gao, Y. (2024). A Survey on LoRA of Large Language Models. 1–144. https://doi.org/10.1007/s11704-024-40663-9

Newzoo. (2021). RPGs are mobile’s biggest genre by revenues: How do gamers across East and West engage with the genre?https://newzoo.com/insights/articles/rpgs-are-mobiles-biggest-genre-by-revenues-how-do-gamers-across-east-and-west-engage-with-the-genre

Ou, J., Lu, J., Liu, C., Tang, Y., Zhang, F., Zhang, D., & Gai, K. (2024). DialogBench: Evaluating LLMs as Human-like Dialogue Systems. https://arxiv.org/abs/2311.01677

Radež, G., & Bohak, C. (2024). Integrating Environmental Awareness Into NPCs?: Contextual Conversational Interaction in Games.

Ren, M. (2024). Advancements and Applications of Large Language Models in Natural Language Processing?: A Comprehensive Review. 0, 55–63. https://doi.org/10.54254/2755-2721/97/20241406

Shahsavar, Y., & Choudhury, A. (2023). User Intentions to Use ChatGPT for Self-Diagnosis and Health-Related Purposes: Cross-sectional Survey Study. JMIR Hum Factors, 10, e47564. https://doi.org/10.2196/47564

Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, ?., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30.

Warpefelt, H., & Verhagen, H. (2016). A model of non-player character believability Keywords.

Xu, Z., Jain, S., & Kankanhalli, M. (2024). Hallucination is inevitable: An innate limitation of large language models. arXiv preprint arXiv:2401.11817

Zhang, Q., Wen, R., Hendra, L. B., Ding, Z., & LC, R. (2025). Can AI Prompt Humans? Multimodal Agents Prompt Players’ Game Actions and Show Consequences to Raise Sustainability Awareness. https://arxiv.org/abs/2409.08486

Downloads

Published

2025-08-19

How to Cite

Mulyana, A., Wibisono, Y., & Anisyah, A. (2025). Non-Playable Characters Based On Large Language Models For Role Playing Games (RPG). Brilliance: Research of Artificial Intelligence, 5(2), 785–792. https://doi.org/10.47709/brilliance.v5i2.6779