Summary
Creating game scenes often involves complex tools and experience tied to one game engine, making moving those scenes to a new engine difficult. The authors introduce SceneAgent, a system that separates the scene’s state and knowledge from engine specifics, letting the same scene building process be reused on different engines. They tested SceneAgent on many indoor and outdoor scene prompts and found it better matches human preferences than other methods. This system also distills reusable skills from previous work, improving how well scenes meet their prompts and how complete they are. By isolating backend details, SceneAgent makes it easier to switch engines without losing the scene-building progress or knowledge.
What this means in practice
- •For game developers: Reuse game scene building workflows and knowledge across different game engines to speed up asset creation when switching platforms.
- •For interactive media designers: Ensure consistent scene creation logic while adapting scene exports to varying backend requirements for diverse interactive applications.
Authors
Xingyi Li, Jiahao Yang, Yiqin Zhu, Jingwen Ye, Yang Sun, Weidong Zhang
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.