Engineering and Technology
| Open Access |
DOI: AI as a Catalyst for Automation in High-Level Game Design for Adaptive Game Structures and Enhancing Player Engagement
Oleh Riazanov , Head of Game Design, Bini Games Kitchener, CanadaAbstract
The paper discusses the great change at the high end of game development brought about by generative artificial intelligence — not simply a minor tooling upgrade but rather a machine that can be used in automating the building of adaptive systems and increasing the gravitational pull of engagement for players. At a studio level, adoption has already moved beyond pilot projects to institutional practice-a shift that turns mere efficiency gains into matters of existence for quite many teams. The paper’s novel input is a neat merge of three paths: first, the lift of a game’s “skeleton” to a formal meta-model that lets big language models set up event graphs; second, a change in how hardship is made real — moving from simple time factors (D1/D7) to group-level keeping and leaving-risk hints so that tuning helps long-term involvement rather than short-term win rates; and third, the use of a feedback loop — watcher-helper sending possible changes to a skilled checker, with checker fixes sent back as top-notch training samples to lessen false guesses methodically. AI-fueled automation substantially speeds up prototyping and can enhance extended player engagement; however, these advances are precarious — dependent on legally verifiable data origin, strict dual-path (algorithmic + human) examination, and transparent intervention mechanisms — if not present, then adaptive systems may stray from customization to hidden control. This paper aims at academics and business professionals who seek disciplined, practical methods for implementing AI in design while maintaining creative freedom and responsibility.
Keywords
artificial intelligence, automation of game design, adaptive game structures, player engagement, dynamic difficulty
References
Amplitude. (2025). Interpret your retention analysis. Amplitude. https://amplitude.com/docs/analytics/charts/retention-analysis/retention-analysis-interpret
Bycer, J. (2014). Understanding High and Low-Level Game Design. Game Developer. https://www.gamedeveloper.com/design/understanding-high-and-low-level-game-design
Elderkin, B. (2025). GDC 2025 State of the Game Industry: Devs weigh in on layoffs, AI, and more. Game Developer. https://www.gamedeveloper.com/business/gdc-2025-state-of-the-game-industry-devs-weigh-in-on-layoffs-ai-and-more
Fisher, N., & Kulshreshth, A. K. (2024). Exploring Dynamic Difficulty Adjustment Methods for Video Games. Virtual Worlds, 3(2), 230–255. https://doi.org/10.3390/virtualworlds3020012
GDC. (2025). State of the Game Industry. Game Developers Conference. https://gdconf.com/state-game-industry/
Kachwala, Z. (2025a). Nearly 90% of video game developers utilize AI agents, according to a Google study. Reuters. https://www.reuters.com/business/nearly-90-videogame-developers-use-ai-agents-google-study-shows-2025-08-18/
Kachwala, Z. (2025b, June 17). The delay of GTA VI weighs on global videogame market growth, data shows. Reuters. https://www.reuters.com/business/media-telecom/gta-vi-delay-weighs-global-videogame-market-growth-data-shows-2025-06-17/
McGuire, M. (2024). Roblox’s Road to 4D Generative AI. Roblox Corporate. https://corp.roblox.com/newsroom/2024/06/robloxs-road-to-4d-generative-ai
Mi, Q., & Gao, T. (2025). Engagement-Oriented Dynamic Difficulty Adjustment. Applied Sciences, 15(10). https://doi.org/10.3390/app15105610
Microsoft. (2025, May). Experimentation. Microsoft. https://learn.microsoft.com/en-us/gaming/playfab/live-service-management/game-configuration/experiments/
NVIDIA Developer. (n.d.). NVIDIA ACE for Games. NVIDIA Developer. Retrieved August 9, 2025, from https://developer.nvidia.com/ace-for-games
Peters, J. (2025, January 7). Nvidia’s AI NPCs are no longer chatbots — they’re your new PUBG teammate. The Verge. https://www.theverge.com/2025/1/6/24337949/nvidia-ace-ai-npcs-pubg-ally-teammate
Sudhakaran, S., González-Duque, M., Glanois, C., Freiberger, M., Najarro, E., & Risi, S. (2023). MarioGPT: Open-Ended Text2Level Generation through Large Language Models. Arxiv. https://doi.org/10.48550/arxiv.2302.05981
Unity. (n.d.). A/B testing. Unity. Retrieved August 12, 2025, from https://docs.unity.com/ugs/solutions/manual/ABTest
Zhang, B., Xu, M., & Pan, Z. (2025). Human-AI Collaborative Game Testing with Vision Language Models. Arxiv. https://doi.org/10.48550/arxiv.2501.11782
Article Statistics
Copyright License
Copyright (c) 2025 Oleh Riazanov
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain the copyright of their manuscripts, and all Open Access articles are disseminated under the terms of the Creative Commons Attribution License 4.0 (CC-BY), which licenses unrestricted use, distribution, and reproduction in any medium, provided that the original work is appropriately cited. The use of general descriptive names, trade names, trademarks, and so forth in this publication, even if not specifically identified, does not imply that these names are not protected by the relevant laws and regulations.