Inteligência Artificial no Processo de Design e Desenvolvimento de Jogos Digitais - Mapeamento Sistemático da Literatura
Resumo
Introdução: O mercado de games atingiu US$ 188,8 bilhões em 2025, impulsionando a busca por eficiência no desenvolvimento. Modelos de Linguagem de Grande Escala (LLMs) surgem como ferramentas promissoras, mas sua integração ainda é limitada. Objetivo: O objetivo é realizar um Mapeamento Sistemático da Literatura, visando identificar o estado da arte nesse domínio. Metodologia: O MSL seguiu o protocolo de Kitchenham e Charters, consultando cinco bases de dados e selecionando 17 de 467 estudos primários. Resultados: A IA concentra-se nas fases de development e design, com RPG como gênero mais frequente. LLMs foram a técnica predominante, enquanto a avaliação priorizou métricas de desempenho em detrimento da experiência do usuário. Este estudo evidencia a lacuna entre o foco técnico das implementações de IA e a necessidade de considerar a experiência do jogador, orientando pesquisas futuras para soluções mais centradas no usuário.
Palavras-chave:
Jogos Digitais, Design e Desenvolvimento de Jogos Digitais, Mapeamento Sistemático, Inteligência Artificial
Referências
Annepaka, Y. e Pakray, P. (2025). Large language models: A survey of their development, capabilities, and applications. Knowledge and Information Systems, 67:2967–3022.
Aribarg, A. e Jintawatsakoon, S. (2024). Ai-enhanced illustration: A time and cost-efficient solution for indie developers. In 2024 8th International Conference on Information Technology (InCIT), pages 417–422. IEEE.
Arnab, S., Lim, T., Carvalho, M. B., Bellotti, F., De Freitas, S., Louchart, S., Suttie, N., Berta, R., e De Gloria, A. (2015). Mapping learning and game mechanics for serious games analysis. British Journal of Educational Technology, 46(2):391–411.
Basili, V. R. (1992). Software modeling and measurement: the Goal/Question/Metric paradigm. University of Maryland at College Park.
Böck, M., Habchi, S., Nayrolles, M., e Cito, J. (2023). Performance prediction from source code is task and domain specific. In 2023 IEEE/ACM 31st International Conference on Program Comprehension (ICPC), pages 35–42. IEEE.
Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020). Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
Callele, D., Neufeld, E., e Schneider, K. (2024). A stakeholder-centric framework for game design and development. Entertainment Computing, 49:100614.
Chen, D., Wang, H., Huo, Y., Li, Y., e Zhang, H. (2023). Gamegpt: Multi-agent collaborative framework for game development. arXiv preprint arXiv:2310.08067.
Croissant, M., Frister, M., Schofield, G., e McCall, C. (2024). An appraisal-based chain-of-emotion architecture for affective language model game agents. Plos one, 19(5):e0301033.
Fu, Y., Cheng, Z., Liao, Y., Wang, J., Wang, R., Yue, G., Lv, C., e Zhao, B. (2025). Gamemld: A game-sourced motion-language dataset for stylized motion generation. In 2025 IEEE International Conference on Multimedia and Expo (ICME), pages 1–6. IEEE.
Gaglio, G. F., Vinanzi, S., Cangelosi, A., e Chella, A. (2024). Intention reading architecture for virtual agents. In International Conference on Social Robotics, pages 488–497. Springer.
Goodfellow, I., Bengio, Y., e Courville, A. (2016). Deep Learning. MIT Press.
He, Z., Zou, X., Wu, P., Fan, L., e Li, X. (2024). Creating and experiencin 3d immersion using generative 2d diffusion: an integrated framework. In 2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), pages 1–6. IEEE.
Hou, X., Zhao, Y., Liu, Y., Yang, Z., Wang, K., Li, L., Luo, X., Lo, D., Grundy, J., e Wang, H. (2024). Large language models for software engineering: A systematic literature review. ACM Transactions on Software Engineering and Methodology, 33(8):1–79.
Jahangiri, M. M. e Rahmani, P. (2024). Balancing game satisfaction and resource efficiency: Llm and pursuit learning automata for npc dialogues. In 2024 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), pages 1–6. IEEE.
Keele, S. et al. (2007). Guidelines for performing systematic literature reviews in software engineering.
Kelly, H., Howell, K., Glinert, E., Holding, L., Swain, C., Burrowbridge, A., e Roper, M. (2007). How to build serious games. Communications of the ACM, 50(7):45–49.
Kitchenham, B., Madeyski, L., e Budgen, D. (2023). Segress: Software engineering guidelines for reporting secondary studies. IEEE Transactions on Software Engineering, 49(3):1273–1298.
Klinkert, L., Buongiorno, S., e Clark, C. (2024). Driving generative agents with their personality. arxiv.
Kumaran, V., Rowe, J., Mott, B., e Lester, J. (2023). Scenecraft: Automating interactive narrative scene generation in digital games with large language models. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, volume 19, pages 86–96.
Lee, J. e Lee, J. (2023). Generative ai for the super game designer. In Proceedings of the International Conferences on Interfaces and Human Computer Interaction 2023, IHCI 2023; Computer Graphics, Visualization, Computer Vision and Image Processing 2023, CGVCVIP 2023; and Game and Entertainment Technologies 2023, GET 2023, pages 203–212. IADIS Press.
Lee, J., Yoon, S., Shim, H., e Yoo, Y. (2025). Development of an llm-based chatbot to support learnability in stardew valley: A diary study approach. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, CHI ’25, New York, NY, USA. Association for Computing Machinery.
Madar, O. e Fried, O. (2025). Tiled diffusion. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 7795–7804.
Matias, B. C., Freire, S., Freitas, J., Fronchetti, F., Damevski, K., e Spinola, R. (2026). A survey on large language model impact on software evolvability and maintainability. arXiv preprint arXiv:2601.20879.
Muratet, M. e Garbarini, D. (2020). Accessibility and serious games: What about entity-component-system software architecture? In Games and Learning Alliance (GALA). Springer.
Newzoo (2026). Global games market to generate $175.8 billion in 2021. Accessed: 2026-03-22.
Nguyen, V. V. e Nguyen, T. V. (2024). Large language models in software engineering: A systematic review and vision. Journal of Education for Sustainable Innovation, 2(2):146–156.
Paduraru, C., Paduraru, M., e Stefanescu, A. (2025). Enhancing game ai behaviors with large language models and agentic ai. In Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering, pages 286–296.
Rao, S., Xu, W., Xu, M., Leandro, J., Lobb, K., DesGarennes, G., Brockett, C. J., e Dolan, W. B. (2024). Collaborative quest completion with llm-driven non-player characters in minecraft. ArXiv, abs/2407.03460.
Rougas, B. (2016). A model-driven framework for educational game design. International Journal of Serious Games, 3(3):19–37.
Santos, C. M. d. C., Pimenta, C. A. d. M., e Nobre, M. R. C. (2007). A estratégia pico para a construção da pergunta de pesquisa e busca de evidências. Revista latino-americana de enfermagem, 15:508–511.
Schaffer, O. e Isbister, K. (2024). A design framework for reflective play. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems, pages 1–17. ACM.
Singh, D., Banerjee, J., e Pandey, J. (2025). Ai-driven npc dialogues for immersive gameplay: Integrating openai’s nlp technology in unity-based games. In 2025 International Conference on Intelligent Computing and Virtual & Augmented Reality Simulations (ICVARS), pages 50–55. IEEE.
Siriaraya, P., Visch, V., Vermeeren, A., e Bas, M. A. (2018). A cookbook method for persuasive game design. International Journal of Serious Games, 5(1):37–56.
Spjut, J. (2025). A generative ai game jam case study from october 2024. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 612–618.
Togelius, J., Yannakakis, G. N., Stanley, K. O., e Browne, C. (2011). Search-based procedural content generation: A taxonomy and survey. IEEE Transactions on Computational Intelligence and AI in Games, 3(3):172–186.
Tower, S. (2021). State of mobile gaming 2021. Accessed: 2025-04-17.
Unity Technologies (2026). 2026 game development report. [link]. Acesso em: 25 mar. 2026.
Wang, C., Tang, L., Yuan, M., Yu, J., Xie, X., e Bu, J. (2025). Leveraging llm agents for automated video game testing. arXiv preprint arXiv:2509.22170.
Wang, Q., Zhao, Y., e Li, J. (2024). A survey on large language models for game design and development. arXiv preprint arXiv:2411.00308. Preprint.
Winn, B. (2008). The design, play, and experience framework. In Ferdig, R. E., editor, Handbook of Research on Effective Electronic Gaming in Education, pages 1010– 1024. IGI Global.
Worldpay (2021). Microtransactions: Next big thing? Accessed: 2025-04-17.
Wu, Y., Li, X., e Zhang, H. (2025). Integrating game design, design thinking, and computational thinking: A systematic review. Humanities and Social Sciences Communications, 12(1):1–15.
Xiao, C. e Yang, Z. (2025). Llms may not be human-level players, but they can be testers: Measuring game difficulty with llm agents. Proceedings of the ACM on Human-Computer Interaction, 9(6):1097–1123.
Xu, F. F., Alon, U., Neubig, G., e Hellendoorn, V. J. (2022). A systematic evaluation of large language models of code. arXiv preprint arXiv:2202.13169.
Yannakakis, G. N. e Togelius, J. (2018). Artificial intelligence and games, volume 2. Springer.
Aribarg, A. e Jintawatsakoon, S. (2024). Ai-enhanced illustration: A time and cost-efficient solution for indie developers. In 2024 8th International Conference on Information Technology (InCIT), pages 417–422. IEEE.
Arnab, S., Lim, T., Carvalho, M. B., Bellotti, F., De Freitas, S., Louchart, S., Suttie, N., Berta, R., e De Gloria, A. (2015). Mapping learning and game mechanics for serious games analysis. British Journal of Educational Technology, 46(2):391–411.
Basili, V. R. (1992). Software modeling and measurement: the Goal/Question/Metric paradigm. University of Maryland at College Park.
Böck, M., Habchi, S., Nayrolles, M., e Cito, J. (2023). Performance prediction from source code is task and domain specific. In 2023 IEEE/ACM 31st International Conference on Program Comprehension (ICPC), pages 35–42. IEEE.
Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020). Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
Callele, D., Neufeld, E., e Schneider, K. (2024). A stakeholder-centric framework for game design and development. Entertainment Computing, 49:100614.
Chen, D., Wang, H., Huo, Y., Li, Y., e Zhang, H. (2023). Gamegpt: Multi-agent collaborative framework for game development. arXiv preprint arXiv:2310.08067.
Croissant, M., Frister, M., Schofield, G., e McCall, C. (2024). An appraisal-based chain-of-emotion architecture for affective language model game agents. Plos one, 19(5):e0301033.
Fu, Y., Cheng, Z., Liao, Y., Wang, J., Wang, R., Yue, G., Lv, C., e Zhao, B. (2025). Gamemld: A game-sourced motion-language dataset for stylized motion generation. In 2025 IEEE International Conference on Multimedia and Expo (ICME), pages 1–6. IEEE.
Gaglio, G. F., Vinanzi, S., Cangelosi, A., e Chella, A. (2024). Intention reading architecture for virtual agents. In International Conference on Social Robotics, pages 488–497. Springer.
Goodfellow, I., Bengio, Y., e Courville, A. (2016). Deep Learning. MIT Press.
He, Z., Zou, X., Wu, P., Fan, L., e Li, X. (2024). Creating and experiencin 3d immersion using generative 2d diffusion: an integrated framework. In 2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), pages 1–6. IEEE.
Hou, X., Zhao, Y., Liu, Y., Yang, Z., Wang, K., Li, L., Luo, X., Lo, D., Grundy, J., e Wang, H. (2024). Large language models for software engineering: A systematic literature review. ACM Transactions on Software Engineering and Methodology, 33(8):1–79.
Jahangiri, M. M. e Rahmani, P. (2024). Balancing game satisfaction and resource efficiency: Llm and pursuit learning automata for npc dialogues. In 2024 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), pages 1–6. IEEE.
Keele, S. et al. (2007). Guidelines for performing systematic literature reviews in software engineering.
Kelly, H., Howell, K., Glinert, E., Holding, L., Swain, C., Burrowbridge, A., e Roper, M. (2007). How to build serious games. Communications of the ACM, 50(7):45–49.
Kitchenham, B., Madeyski, L., e Budgen, D. (2023). Segress: Software engineering guidelines for reporting secondary studies. IEEE Transactions on Software Engineering, 49(3):1273–1298.
Klinkert, L., Buongiorno, S., e Clark, C. (2024). Driving generative agents with their personality. arxiv.
Kumaran, V., Rowe, J., Mott, B., e Lester, J. (2023). Scenecraft: Automating interactive narrative scene generation in digital games with large language models. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, volume 19, pages 86–96.
Lee, J. e Lee, J. (2023). Generative ai for the super game designer. In Proceedings of the International Conferences on Interfaces and Human Computer Interaction 2023, IHCI 2023; Computer Graphics, Visualization, Computer Vision and Image Processing 2023, CGVCVIP 2023; and Game and Entertainment Technologies 2023, GET 2023, pages 203–212. IADIS Press.
Lee, J., Yoon, S., Shim, H., e Yoo, Y. (2025). Development of an llm-based chatbot to support learnability in stardew valley: A diary study approach. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, CHI ’25, New York, NY, USA. Association for Computing Machinery.
Madar, O. e Fried, O. (2025). Tiled diffusion. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 7795–7804.
Matias, B. C., Freire, S., Freitas, J., Fronchetti, F., Damevski, K., e Spinola, R. (2026). A survey on large language model impact on software evolvability and maintainability. arXiv preprint arXiv:2601.20879.
Muratet, M. e Garbarini, D. (2020). Accessibility and serious games: What about entity-component-system software architecture? In Games and Learning Alliance (GALA). Springer.
Newzoo (2026). Global games market to generate $175.8 billion in 2021. Accessed: 2026-03-22.
Nguyen, V. V. e Nguyen, T. V. (2024). Large language models in software engineering: A systematic review and vision. Journal of Education for Sustainable Innovation, 2(2):146–156.
Paduraru, C., Paduraru, M., e Stefanescu, A. (2025). Enhancing game ai behaviors with large language models and agentic ai. In Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering, pages 286–296.
Rao, S., Xu, W., Xu, M., Leandro, J., Lobb, K., DesGarennes, G., Brockett, C. J., e Dolan, W. B. (2024). Collaborative quest completion with llm-driven non-player characters in minecraft. ArXiv, abs/2407.03460.
Rougas, B. (2016). A model-driven framework for educational game design. International Journal of Serious Games, 3(3):19–37.
Santos, C. M. d. C., Pimenta, C. A. d. M., e Nobre, M. R. C. (2007). A estratégia pico para a construção da pergunta de pesquisa e busca de evidências. Revista latino-americana de enfermagem, 15:508–511.
Schaffer, O. e Isbister, K. (2024). A design framework for reflective play. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems, pages 1–17. ACM.
Singh, D., Banerjee, J., e Pandey, J. (2025). Ai-driven npc dialogues for immersive gameplay: Integrating openai’s nlp technology in unity-based games. In 2025 International Conference on Intelligent Computing and Virtual & Augmented Reality Simulations (ICVARS), pages 50–55. IEEE.
Siriaraya, P., Visch, V., Vermeeren, A., e Bas, M. A. (2018). A cookbook method for persuasive game design. International Journal of Serious Games, 5(1):37–56.
Spjut, J. (2025). A generative ai game jam case study from october 2024. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 612–618.
Togelius, J., Yannakakis, G. N., Stanley, K. O., e Browne, C. (2011). Search-based procedural content generation: A taxonomy and survey. IEEE Transactions on Computational Intelligence and AI in Games, 3(3):172–186.
Tower, S. (2021). State of mobile gaming 2021. Accessed: 2025-04-17.
Unity Technologies (2026). 2026 game development report. [link]. Acesso em: 25 mar. 2026.
Wang, C., Tang, L., Yuan, M., Yu, J., Xie, X., e Bu, J. (2025). Leveraging llm agents for automated video game testing. arXiv preprint arXiv:2509.22170.
Wang, Q., Zhao, Y., e Li, J. (2024). A survey on large language models for game design and development. arXiv preprint arXiv:2411.00308. Preprint.
Winn, B. (2008). The design, play, and experience framework. In Ferdig, R. E., editor, Handbook of Research on Effective Electronic Gaming in Education, pages 1010– 1024. IGI Global.
Worldpay (2021). Microtransactions: Next big thing? Accessed: 2025-04-17.
Wu, Y., Li, X., e Zhang, H. (2025). Integrating game design, design thinking, and computational thinking: A systematic review. Humanities and Social Sciences Communications, 12(1):1–15.
Xiao, C. e Yang, Z. (2025). Llms may not be human-level players, but they can be testers: Measuring game difficulty with llm agents. Proceedings of the ACM on Human-Computer Interaction, 9(6):1097–1123.
Xu, F. F., Alon, U., Neubig, G., e Hellendoorn, V. J. (2022). A systematic evaluation of large language models of code. arXiv preprint arXiv:2202.13169.
Yannakakis, G. N. e Togelius, J. (2018). Artificial intelligence and games, volume 2. Springer.
Publicado
29/09/2026
Como Citar
SERRA, Cristiano Barroso; CLASSE, Tadeu Moreira de; SOUSA, Henrique Prado de Sá.
Inteligência Artificial no Processo de Design e Desenvolvimento de Jogos Digitais - Mapeamento Sistemático da Literatura. In: SIMPÓSIO BRASILEIRO DE JOGOS E ENTRETENIMENTO DIGITAL (SBGAMES), 25. , 2026, Goiânia/GO.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 81-93.
DOI: https://doi.org/10.5753/sbgames.2026.25182.
