OpenGame: Open Agentic Coding for Games

AK's Picks LLM PTSAD RLHF Agent Agent Eval Benchmarks Autonomous Workflows AI Systems and Hardware CACRR Text-to-Code
2159
2026年04月20日
游戏开发处于创意设计与复杂软件工程的交汇点，要求游戏引擎、实时循环机制以及跨多个文件的高度耦合状态之间实现协同运作。尽管大型语言模型（LLMs）和代码智能体目前已能轻松完成孤立的编程任务，但当被要求依据高层级设计规范从零构建一款可完整运行的游戏时，它们却屡屡受挫——往往因跨文件不一致、场景连接断裂以及逻辑自相矛盾等问题而彻底失效。为弥合这一关键鸿沟，我们推出了 OpenGame：首个专为端到端网页游戏创作而设计的开源智能体框架。其核心是“游戏技能”（Game Skill），一种可复用、持续演进的能力模块，由两部分构成：一是“模板技能”（Template Skill），它通过经验积累不断扩充项目骨架模板库；二是“调试技能”（Debug Skill），它维护一套动态更新、经实证验证的修复协议。二者协同作用，使智能体不仅能快速搭建稳健的架构基础，更能系统性地定位并修复集成层面的错误，而非仅修补孤立的语法层面缺陷。驱动该框架的是 GameCoder-27B——一款专精于游戏引擎掌握的代码大语言模型，其能力通过三阶段训练流程持续强化：持续预训练（continual pre-training）、监督微调（supervised fine-tuning）以及以实际执行效果为反馈信号的强化学习（execution-grounded reinforcement learning）。鉴于验证交互式可玩性本质上远比检查静态代码复杂得多，我们进一步提出了 OpenGame-Bench：一个面向智能体生成游戏的评估流水线。该流水线依托无头浏览器执行（headless browser execution）与视觉语言模型（VLM）评判，从“构建健康度”（Build Health）、“视觉可用性”（Visual Usability）和“意图对齐度”（Intent Alignment）三个维度对生成结果进行综合评分。在涵盖150个多样化游戏需求提示的基准测试中，OpenGame 刷新了当前最佳性能纪录。我们期望 OpenGame 能推动代码智能体突破离散式软件工程问题的局限，真正迈向构建复杂、交互式的真实世界应用。本框架将完全开源。
Game development sits at the intersection of creative design and intricate software engineering, demanding the joint orchestration of game engines, real-time loops, and tightly coupled state across many files. While Large Language Models (LLMs) and code agents now solve isolated programming tasks with ease, they consistently stumble when asked to produce a fully playable game from a high-level design, collapsing under cross-file inconsistencies, broken scene wiring, and logical incoherence. We bridge this gap with OpenGame, the first open-source agentic framework explicitly designed for end-to-end web game creation. At its core lies Game Skill, a reusable, evolving capability composed of a Template Skill that grows a library of project skeletons from experience and a Debug Skill that maintains a living protocol of verified fixes - together enabling the agent to scaffold stable architectures and systematically repair integration errors rather than patch isolated syntax bugs. Powering this framework is GameCoder-27B, a code LLM specialized for game engine mastery through a three-stage pipeline of continual pre-training, supervised fine-tuning, and execution-grounded reinforcement learning. Since verifying interactive playability is fundamentally harder than checking static code, we further introduce OpenGame-Bench, an evaluation pipeline that scores agentic game generation along Build Health, Visual Usability, and Intent Alignment via headless browser execution and VLM judging. Across 150 diverse game prompts, OpenGame establishes a new state-of-the-art. We hope OpenGame pushes code agents beyond discrete software engineering problems and toward building complex, interactive real-world applications. Our framework will be fully open-sourced.
许愿