AI Native Games: A Survey and Roadmap
2026-07-01 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors explain that just adding AI to games doesn't make them truly AI-native; instead, AI-native games rely on generative AI as an essential part of how you play. They define AI-native games by whether removing the AI would change the core gameplay completely. After studying 53 examples, they found most use language-based designs like storytelling and knowledge puzzles, while other AI uses are less common. The authors highlight that good AI-native games need stable rules and goals to make the AI's open-ended creations meaningful and playable. They also suggest future research directions like better control of AI, safety, and multi-agent AI systems.
Generative AIAI-native gamesCore gameplay loopProcedural content generationNarrative adventureSemantic adjudicationPlayer agencyMulti-agent simulationGame mechanicsControllable generation
Authors
Zhiyue Xu, Fandi Meng, Kaijie Xu, Clark Verbrugge, Simon Lucas, Jian Zhao
Abstract
Generative AI now enables games to produce dialogue, quests, characters, images, and worlds at runtime. Yet generation alone does not make a game AI-native, nor does it guarantee playability. This paper defines AI-native games by whether runtime generative AI is constitutive of the core loop: if the AI component were removed or trivially replaced, the central form of play would collapse or become fundamentally different. This counterfactual criterion separates AI-native games from AI-augmented games, boundary artifacts, chatbots, tavern-style role-play, procedural content generation, and AI-assisted production. Using this definition, we screen candidate artifacts and analyze 53 publicly available AI-native games and prototypes. We introduce a dual-axis G/N taxonomy: the G-axis captures player-facing game type, while the N-axis captures the dominant AI mechanic that makes generative AI indispensable to play. The corpus is concentrated around language-forward designs, especially narrative adventure, epistemic interaction, and generative narrative, while categories such as semantic adjudication, multi-agent simulation, generative construction, and relationship/companion play remain less represented. We argue that the central design problem is organizing semantic openness into stable gameplay. AI-native design depends on mechanical invariants: goals, rules, state, feedback, pacing, and player agency that make open-ended AI outputs interpretable and consequential. We conclude with a roadmap for controllable generation, AI-as-mechanic design, multimodal and multi-agent systems, inference economics, evaluation, safety, and regulation.