GAMEGO: Training Game-Dev Agents with Synthetic Trajectories Anchored in Real-World Assets
中文摘要
GAMEGO通过合成轨迹与真实素材训练智能体,实现复杂网页游戏的端到端直接生成。
English Summary
GAMEGO trains coding agents using synthetic trajectories and real-world assets for direct, end-to-end synthesis of complex browser-based games.
arXiv:2610.06910v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) have demonstrated remarkable capabilities in web front-end execution, with browser-based game generation emerging as a particularly prominent frontier. While previous efforts frequently rely on complex multi-turn workflows or focus on static game evaluation benchmarks, this work targets direct end-to-end real-world game synthesis driven by coding agents. However, generating complex games directly from sparse user queries often forces coding agents to make underspecified assumptions, yielding incomplete mechanics, disconnected gameplay flows, and limited visual aesthetics. To resolve this issue, this paper presents GameGo, a scalable framework that systematically transforms brief game seeds into comprehensive Product Requirements Documents grounded in industry game-development practices. To retain core gameplay constraints without restricting design exploration, GameGo uses task-specific dynamic compression to maximize information density while preserving instruction following. Based on this pipeline, GameGoData is constructed with 55,060 development trajectories across 2D, 2.5D, and 3D g…