AgentGarten：面向进化智能体的代码世界

AI 摘要

该论文提出 AgentGarten 框架，将模拟器与游戏引擎同共享神经渲染器耦合，构建兼具状态一致性与真实视觉分布的实时交互环境。渲染器通过适配预训练视频模型并采用 Adversarial Forcing 蒸馏实现实时推理。实验显示智能体仅需 4 轮即可学习，而传统强化学习需数百万轮，且新世界可用代码编写并通过同一接口渲染，实现环境与智能体共同扩展。

正文节选

AgentGarten: Code Worlds for Evolving Agents Abstract Interactive virtual worlds allow agents to learn through exploration and interaction. What agents can learn is bounded by the environments they practice in, which must be faithful, with consistent state, rules, and dynamics, and realistic, with observations that follow the real-world visual distributions. Achieving both across diverse worlds remains a bottleneck. We introduce AgentGarten, a framework that couples simulators and game engines w

发布时间：—

抓取时间：2026-10-09 18:59

来源机构：Hugging Face