cs.CVNov 13, 2026

SceneAgent: A Multi-Agent Framework for Portable Game Scene Generation

Authors: Xingyi Li, Jiahao Yang, Yiqin Zhu, Jingwen Ye, Yang Sun, Weidong Zhang

Organizations: Tencent · Fudan University

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.

Figures & tables

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Code4Scene: Benchmarking Coding Agents for Constructing and Editing 3D Scenes

    Sep 29, 2026Xiaokang Ye, Siddhant Hitesh Mantri, Zimeng Chen +6AI Coding Agents3D Scene Editing

  2. SceneMosaic: Efficient and Diverse Simulation-Ready Scene Generation via Hybrid Agentic Layout Evolution

    Sep 4, 2026Xingjian Ran, Xiaoye Mo, Sihao Liu +33D Scene Generation3D Scene Layout Generation

  3. Scene-Designer: Learning Design Intelligence for Agentic 3D Scene Generation

    Oct 16, 2026Xuanyu Liu, Hongyan Feng, Miao Pan +53D Scene GenerationIndoor Scene Generation