AI Native Games: A Survey and Roadmap

2026-07-01

AI Summary

This study defines and systematically investigates “AI-native games”—games whose core gameplay is fundamentally centered on generative AI—and argues that such games must embed generative AI within their core gameplay loop. By introducing a novel counterfactual criterion and a dual-axis G/N classification framework, the authors distinguish AI-native from AI-enhanced games among 53 publicly available cases and formulate the design principle of “mechanical invariants.” Employing qualitative analysis and theoretical induction, the research focuses on language model–driven interaction mechanisms, revealing a current design landscape dominated by narrative adventure genres. It further identifies promising directions such as multi-agent simulation and proposes a forward-looking roadmap addressing controllable generation, evaluation metrics, and safety considerations.

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.

Problem

• AI-native games
• generative AI
• game design
• semantic openness
• playability

Innovation

• AI-native games
• generative AI
• core gameplay loop
• G/N taxonomy
• mechanical invariants