VibeGame：提示词到游戏开发，AI原生引擎与自进化对抗智能体团队
原标题：Paper page - VibeGame: Prompt-to-Game Development with AI-Native Engine and Self-Evolving Adversarial Agent Team
AI 摘要
研究团队提出 VibeGame 框架，通过 AI 原生游戏引擎和由八个专用智能体组成的对抗式智能体团队，从自然语言提示（可选参考图）生成完整可玩的 2D 游戏项目，并引入免训练的自进化机制，将已验收项目蒸馏为可复用的骨架、模块与协作契约。在 GameCraft-Bench 的 30 个任务上，VibeGame 在 P2G 设置下分别以 GPT-5.6-Luna 和 GPT-6.1-Sol 为底层模型，比最强基线框架高出 11.70 分和 4.19 分。
正文节选
VibeGame: Prompt-to-Game Development with AI-Native Engine and Self-Evolving Adversarial Agent Team Abstract VibeGame is a framework that uses specialized adversarial agents and an AI-native engine to build complete 2D games from natural-language prompts with interactive validation and self-evolving reusable components. Large language model agents have enabled software development through natural-language interaction, but extending this paradigm to end-to-end game development remains challenging