arXiv：cs.AI· Tencent Multimodal RL Team, Xiangxin Zhou, Jiaqi Tang, Ke Ma, Wenhao Yang, Jiarui Yao, Boye Niu, Haiyang Guo, Yifei Zhao, Huanjin Yao, Pu Jian, Ruihuang Li, Haitao Wu, Yushi Huang, Xiangyan Liu, Yan Sun, Kaixin Li, Tianyu Pang·· 16 小时前
腾讯多模态 RL 团队发布 Game-Creation-Agents：从自然语言到可运行 Phaser 4 浏览器游戏
Game-Creation-Agents: Autonomous Game Production
AI 导读
腾讯多模态 RL 团队提出 Game-Creation-Agents（GCA），可将自然语言请求转化为可运行的 Phaser 4 浏览器游戏。该流程先构建多模态游戏设计文档，投影为运行时脚手架、机器可读契约与确定性测试，再由八个专用智能体串行实现场景、并行生产素材并合并为单一构建，经真实 UI 检查和代码盲评审后决定是否发布。
正文
Authors:Tencent Multimodal RL Team: Xiangxin Zhou, Jiaqi Tang, Ke Ma, Wenhao Yang, Jiarui Yao, Boye Niu, Haiyang Guo, Yifei Zhao, Huanjin Yao, Pu Jian, Ruihuang Li, Haitao Wu, Yushi Huang, Xiangyan Liu, Yan Sun, Kaixin Li, Tianyu Pang
Abstract:Game-Creation-Agents (GCA) turns a natural-language request into a runnable Phaser 4 browser game. The pipeline first builds a multimodal game design document that couples mechanics and scene contracts to grounded visual references. It then projects that document into a runtime scaffold, machine-readable contracts, and deterministic tests. Eight specialized agents next carry out production: scenes are implemented serially, assets are produced in parallel, and one reduced manifest joins the two branches into a single build. Build-linked real-UI checks and a code-blind critic then verify that build and decide whether the game may ship. Each blocker returns to the agent that owns the affected artifact for a bounded repair, and the game is released once all the gates pass. We evaluate finished games separately, through their rendered interfaces alone, over prompt-matched tasks run under a common protocol. GCA achieves stronger requirement satisfaction, core mechanics, content depth, and functional visuals than a comparable open pipeline. In a side-by-side human study, raters also score GCA's games higher on every dimension and prefer them overall.
| Comments: | this https URL |
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.16776 [cs.AI] |
| (or arXiv:2610.16776v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.16776 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jiaqi Tang [view email]
[v1]
Mon, 12 Oct 2026 13:34:08 UTC (15,759 KB)
来源：arXiv：cs.AI · arxiv.org