跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-22AI 評分46

VibeGame:以 AI 原生引擎和自我演進對抗式智能體團隊實現提示詞到遊戲開發

VibeGame: Prompt-to-Game Development with AI-Native Engine and Self-Evolving Adversarial Agent Team

AI 導讀

VibeGame 利用 AI 原生引擎及八個專門智能體,從自然語言提示詞建立完整的 2D 遊戲專案,並支援互動驗證。在 GameCraft-Bench 子集上,使用 P2G 的 VibeGame 持續勝過採用相同底層模型的多種智能體框架,包括 GPT-6.1-Sol。它亦透過免訓練的自我演進機制,將已完成並獲接納的專案整理成可重用元件。

正文

Published on Oct 22

#1 Paper of the day

Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

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. Building a playable game requires coordinating code, scenes, assets, animations, physics, and configurations, while allowing developers to validate their integrated behavior through interactive testing. We introduce VibeGame, a framework for creating complete 2D game projects from natural-language prompts and optional reference images. Its AI-native game engine represents project state as schema-validated structured text and provides frame-synchronous runtime control, enabling agents to inspect game states, execute actions, and verify behavior at their own pace. Built upon this interface, we design an Adversarial Agent Team of eight specialized agents to separate implementation from review, so that problems are found and fixed through multi-round loops. For each conducted and accepted project, we further introduce a training-free self-evolution mechanism to distill it into reusable skeletons, modules, and collaboration contracts for future development. We evaluate prompt-assets-to-game (PA2G), where agents are given an asset library, and prompt-to-game (P2G), where agents generate their own art. On a GameCraft-Bench subset, VibeGame in P2G consistently outperforms a range of agent harnesses in either P2G or PA2G with the same underlying model, including GPT-6.1-Sol.

View arXiv page View PDF Project page GitHub 284 Add to collection

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.33106 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.33106 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.33106 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co