SceneAgent:用于可移植游戏场景生成的多智能体框架
SceneAgent: A Multi-Agent Framework for Portable Game Scene Generation
AI 导读
研究者提出 SceneAgent,一个跨游戏引擎后端复用场景构建流程与经验的多智能体框架,通过 SceneContext 维护持久世界状态,用后端适配器隔离坐标、资产绑定和导出。
正文 · 原文
Abstract:Moving a scene generator to a new game engine requires more than exporting its final output: planning, construction tools, and stored experience may also depend on the original backend. We present SceneAgent, a multi-agent framework for reusing the construction process and its experience across backends. A canonical SceneContext maintains the evolving world, while backend adapters isolate coordinate conventions, asset bindings, and export. Structured handoffs let fresh Builder sessions query this persistent state without inheriting the full construction transcript. Across generations, human-approved traces are distilled into asset-ID-free Layout skills and semantic Content skills that can be retrieved and recombined. We introduce GameSceneBench, comprising 69 indoor and outdoor prompts. Under a common asset and evaluation protocol, SceneAgent obtains human tie-adjusted preference scores of 78.2-89.4% against five baselines. Ablations show that reusable skills and the multi-agent protocol primarily improve prompt alignment and scene completeness, with additional runtime. Deployment in a second engine preserves the shared construction protocol and skill library while replacing backend integration components. Together, these results support separating persistent scene state, task-local reasoning, and reusable experience for portable scene construction.
| Comments: | Project page: this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.17821 [cs.CV] |
| (or arXiv:2611.17821v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.17821 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xingyi Li [view email]
[v1]
Fri, 13 Nov 2026 06:57:48 UTC (25,103 KB)
来源:arXiv cs.AI · arxiv.org