Player Modeling and Large Language Models: An Interaction-Based Approach
Resumo
Introduction: Adaptive games increasingly demand methods to understand and personalize player experiences. Objective: This study explores the integration of Large Language Models (LLMs) into Player Modeling, leveraging in-game interaction data to analyze player states, predict reference values, and identify dynamic player profiles. Methodology: We propose a Player Model that harnesses the reasoning capabilities of LLMs to generate these insights, enabling adaptive gameplay and personalized player experiences. To demonstrate feasibility, we implemented a proof of concept within the Unity Engine and tested it in a custom-designed game. The evaluation employed G-Eval, an LLM-assisted framework, focusing on the correctness of outputs. Results: The results showed a high average correctness score of 4.044 out of 5.000 across 50 input-output pairs, with 75% of respondes scoring 4 or higher. These findings suggest that LLMs can support Player Modeling, offering a foundation for dynamic difficulty adjustment and personalized game design.
Palavras-chave:
Player Modeling, Large Language Models, Artificial Intelligence
Referências
Bartle, R. (1996). Hearts, clubs, diamonds, spades: Players who suit muds. Journal of MUD Research, 19(1). Charles, D. and Black, M. (2004). Dynamic player modelling: A framework for playercentred digital games. Charles, D., McNeill, M., McAlister, M., Black, M., Moore, A., Stringer, K., Kücklich, J., and Kerr, A. (2005). Player-centred game design: Player modelling and adaptive digital games.
Cheng, Q., Sun, T., Zhang, W., Wang, S., Liu, X., Zhang, M., He, J., Huang, M., Yin, Z., Chen, K., and Qiu, X. (2023). Evaluating hallucinations in chinese large language models.
Cömert, Z. and Samur, Y. (2023). A comprehensive player types model: player head. Interactive Learning Environments, 31(5):2930–2946.
de Lima, E. S., Silva, B. M. C., and Galam, G. T. (2020). Towards the design of adaptive virtual reality horror games: A model of players’ fears using machine learning and player modeling. In 2020 19th Brazilian Symposium on Computer Games and Digital Entertainment (SBGames), pages 171–177, Recife, Brazil. IEEE.
Farooq, S. S. and Kim, K.-J. (2024). Game Player Modeling, chapter 1, pages 1–5. Springer International Publishing, Cham.
Fernandes, P. M., Lopes, M., and Prada, R. (2025). Generating game levels by defining player experiences. In Proceedings of the Twentieth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE ’24, Washington, DC, USA. AAAI Press.
Gallotta, R., Todd, G., Zammit, M., Earle, S., Liapis, A., Togelius, J., and Yannakakis, G. N. (2024). Large language models and games: A survey and roadmap.
Gunjal, A., Yin, J., and Bas, E. (2024). Detecting and preventing hallucinations in large vision language models. Proceedings of the AAAI Conference on Artificial Intelligence, 38(16):18135–18143.
Herbert, B., Charles, D., Moore, A., and Charles, T. (2014a). An investigation of gamification typologies for enhancing learner motivation. In 2014 International Conference on Interactive Technologies and Games, pages 71–78, Nottingham, United Kingdom. IEEE.
Herbert, B., Charles, D., Moore, A., and Charles, T. (2014b). An investigation of gamification typologies for enhancing learner motivation.
Hu, S., Huang, T., Ilhan, F., Tekin, S., Liu, G., Kompella, R., and Liu, L. (2024). A survey on large language model-based game agents.
Kalyan, K. S. (2024). A survey of gpt-3 family large language models including chatgpt and gpt-4. Natural Language Processing Journal, 6:100048.
Liu, Y., Deng, G., Xu, Z., Li, Y., Zheng, Y., Zhang, Y., Zhao, L., Zhang, T., Wang, K., and Liu, Y. (2023a). Jailbreaking chatgpt via prompt engineering: An empirical study.
Liu, Y., Iter, D., Xu, Y., Wang, S., Xu, R., and Zhu, C. (2023b). G-eval: Nlg evaluation using gpt-4 with better human alignment.
Lonergan, R. M., Curry, J., Dhas, K., and Simmons, B. I. (2023). Stratified evaluation of gpt’s question answering in surgery reveals artificial intelligence (ai) knowledge gaps. Cureus, 15(11):e48788.
Mortazavi, F., Moradi, H., and Vahabie, A.-H. (2024). Dynamic difficulty adjustment approaches in video games: a systematic literature review. Multimedia Tools and Applications, 83(35):83227–83274.
Quiñones, J. R. and Fernández-Leiva, A. J. (2020). Xml-based video game description language. IEEE Access, 8:4679–4692.
Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., and Sutskever, I. (2019). Language models are unsupervised multitask learners.
Seyderhelm, A. J. A. and Blackmore, K. (2021). Systematic review of dynamic difficulty adaption for serious games: The importance of diverse approaches. SSRN Electronic Journal, 1(1):1–45.
Souza, C., Oliveira, S., Berretta, L., and Carvalho, S. (2024a). Large language models and dynamic difficulty adjustment: An integration perspective. In Anais Estendidos do XXIII Simpósio Brasileiro de Jogos e Entretenimento Digital, pages 31–36, Porto Alegre, RS, Brasil. SBC.
Souza, C. H. R., de Oliveira, S. S., Berretta, L. O., and Carvalho, S. T. (2025). Extending a mape-k loop-based framework for dynamic difficulty adjustment in single-player games. Entertainment Computing, 52:100842.
Souza, C. H. R., De Oliveira, S. S., Berretta, L. O., and de Carvalho, S. T. (2024b). DDA-MAPEKit: A framework for dynamic difficulty adjustment based on MAPE-K loop. In Proceedings of the 22nd Brazilian Symposium on Games and Digital Entertainment, SBGames’23, page 1–10, New York, NY, USA. Association for Computing Machinery.
Tagliaro, L. R. G. (2022). An implementation of adaptive difficulty systems for challenging video games. Undergraduate Thesis.
Wang, T., Honari-Jahromi, M., Katsarou, S., Mikheeva, O., Panagiotakopoulos, T., Asadi, S., and Smirnov, O. (2024). player2vec: A language modeling approach to understand player behavior in games.
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., and Zhou, D. (2022). Chain-of-thought prompting elicits reasoning in large language models.
Yannakakis, G. N., Spronck, P., Loiacono, D., and André, E. (2013). Player Modeling, chapter 4, pages 45–59. Schloss Dagstuhl – Leibniz-Zentrum für Informatik, Dagstuhl, Germany.
Zhao, W. X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., Dong, Z., Du, Y., Yang, C., Chen, Y., Chen, Z., Jiang, J., Ren, R., Li, Y., Tang, X., Liu, Z., Liu, P., Nie, J.-Y., and Wen, J.-R. (2024). A survey of large language models.
Cheng, Q., Sun, T., Zhang, W., Wang, S., Liu, X., Zhang, M., He, J., Huang, M., Yin, Z., Chen, K., and Qiu, X. (2023). Evaluating hallucinations in chinese large language models.
Cömert, Z. and Samur, Y. (2023). A comprehensive player types model: player head. Interactive Learning Environments, 31(5):2930–2946.
de Lima, E. S., Silva, B. M. C., and Galam, G. T. (2020). Towards the design of adaptive virtual reality horror games: A model of players’ fears using machine learning and player modeling. In 2020 19th Brazilian Symposium on Computer Games and Digital Entertainment (SBGames), pages 171–177, Recife, Brazil. IEEE.
Farooq, S. S. and Kim, K.-J. (2024). Game Player Modeling, chapter 1, pages 1–5. Springer International Publishing, Cham.
Fernandes, P. M., Lopes, M., and Prada, R. (2025). Generating game levels by defining player experiences. In Proceedings of the Twentieth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE ’24, Washington, DC, USA. AAAI Press.
Gallotta, R., Todd, G., Zammit, M., Earle, S., Liapis, A., Togelius, J., and Yannakakis, G. N. (2024). Large language models and games: A survey and roadmap.
Gunjal, A., Yin, J., and Bas, E. (2024). Detecting and preventing hallucinations in large vision language models. Proceedings of the AAAI Conference on Artificial Intelligence, 38(16):18135–18143.
Herbert, B., Charles, D., Moore, A., and Charles, T. (2014a). An investigation of gamification typologies for enhancing learner motivation. In 2014 International Conference on Interactive Technologies and Games, pages 71–78, Nottingham, United Kingdom. IEEE.
Herbert, B., Charles, D., Moore, A., and Charles, T. (2014b). An investigation of gamification typologies for enhancing learner motivation.
Hu, S., Huang, T., Ilhan, F., Tekin, S., Liu, G., Kompella, R., and Liu, L. (2024). A survey on large language model-based game agents.
Kalyan, K. S. (2024). A survey of gpt-3 family large language models including chatgpt and gpt-4. Natural Language Processing Journal, 6:100048.
Liu, Y., Deng, G., Xu, Z., Li, Y., Zheng, Y., Zhang, Y., Zhao, L., Zhang, T., Wang, K., and Liu, Y. (2023a). Jailbreaking chatgpt via prompt engineering: An empirical study.
Liu, Y., Iter, D., Xu, Y., Wang, S., Xu, R., and Zhu, C. (2023b). G-eval: Nlg evaluation using gpt-4 with better human alignment.
Lonergan, R. M., Curry, J., Dhas, K., and Simmons, B. I. (2023). Stratified evaluation of gpt’s question answering in surgery reveals artificial intelligence (ai) knowledge gaps. Cureus, 15(11):e48788.
Mortazavi, F., Moradi, H., and Vahabie, A.-H. (2024). Dynamic difficulty adjustment approaches in video games: a systematic literature review. Multimedia Tools and Applications, 83(35):83227–83274.
Quiñones, J. R. and Fernández-Leiva, A. J. (2020). Xml-based video game description language. IEEE Access, 8:4679–4692.
Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., and Sutskever, I. (2019). Language models are unsupervised multitask learners.
Seyderhelm, A. J. A. and Blackmore, K. (2021). Systematic review of dynamic difficulty adaption for serious games: The importance of diverse approaches. SSRN Electronic Journal, 1(1):1–45.
Souza, C., Oliveira, S., Berretta, L., and Carvalho, S. (2024a). Large language models and dynamic difficulty adjustment: An integration perspective. In Anais Estendidos do XXIII Simpósio Brasileiro de Jogos e Entretenimento Digital, pages 31–36, Porto Alegre, RS, Brasil. SBC.
Souza, C. H. R., de Oliveira, S. S., Berretta, L. O., and Carvalho, S. T. (2025). Extending a mape-k loop-based framework for dynamic difficulty adjustment in single-player games. Entertainment Computing, 52:100842.
Souza, C. H. R., De Oliveira, S. S., Berretta, L. O., and de Carvalho, S. T. (2024b). DDA-MAPEKit: A framework for dynamic difficulty adjustment based on MAPE-K loop. In Proceedings of the 22nd Brazilian Symposium on Games and Digital Entertainment, SBGames’23, page 1–10, New York, NY, USA. Association for Computing Machinery.
Tagliaro, L. R. G. (2022). An implementation of adaptive difficulty systems for challenging video games. Undergraduate Thesis.
Wang, T., Honari-Jahromi, M., Katsarou, S., Mikheeva, O., Panagiotakopoulos, T., Asadi, S., and Smirnov, O. (2024). player2vec: A language modeling approach to understand player behavior in games.
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., and Zhou, D. (2022). Chain-of-thought prompting elicits reasoning in large language models.
Yannakakis, G. N., Spronck, P., Loiacono, D., and André, E. (2013). Player Modeling, chapter 4, pages 45–59. Schloss Dagstuhl – Leibniz-Zentrum für Informatik, Dagstuhl, Germany.
Zhao, W. X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., Dong, Z., Du, Y., Yang, C., Chen, Y., Chen, Z., Jiang, J., Ren, R., Li, Y., Tang, X., Liu, Z., Liu, P., Nie, J.-Y., and Wen, J.-R. (2024). A survey of large language models.
Publicado
30/09/2025
Como Citar
SOUZA, Carlos H. R.; BERRETTA, Luciana O.; CARVALHO, Sérgio T..
Player Modeling and Large Language Models: An Interaction-Based Approach. In: SIMPÓSIO BRASILEIRO DE JOGOS E ENTRETENIMENTO DIGITAL (SBGAMES), 24. , 2025, Salvador/BA.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 630-641.
DOI: https://doi.org/10.5753/sbgames.2025.10174.
