随着人工智能系统从生成文本转向通过持续交互完成目标,，对环境动态进行建模的能力成为一个中心瓶颈。操纵对象, 导航软件, 与其他, 协调或设计实验需要预测环境模型,，但术语世界模型在不同的研究社区中具有不同的含义。我们引入了沿两个轴组织的 "levels x law" 分类法。第一个定义了三个能力级别: L1 Predictor,，它学习单步局部转换运算符; L2 Simulator,，它将它们组合成多步,，尊重领域法则;的动作条件部署；L3 Evolver,，当预测失败时，新证据会自动修改自己的模型。第二个确定了四种管辖法律制度:物理,数字,社会,和科学。这些制度决定了世界模式必须满足哪些约束以及最有可能失败的地方。使用这个框架,，我们综合了 400 多个作品，并总结了 100 多个代表性系统，涵盖基于模型的强化学习, 视频生成, Web 和 GUI 代理, 多代理社会模拟, 和人工智能驱动的科学发现。我们分析方法,故障模式,和跨级别-制度对,的评估实践，提出以决策为中心的评估原则和最小的可重复评估包,，并概述架构指南,开放问题,和治理挑战。由此产生的路线图连接了以前孤立的社区，并绘制了从被动下一步预测到可以模拟,并最终重塑,代理运行环境的世界模型的路径。代码和资源可在 : 此 https URL 处获取。
As AI systems move from generating text to accomplishing goals through sustained interaction, the ability to model environment dynamics becomes a central bottleneck. Agents that manipulate objects, navigate software, coordinate with others, or design experiments require predictive environment models, yet the term world model carries different meanings across research communities. We introduce a "levels x laws" taxonomy organized along two axes. The first defines three capability levels: L1 Predictor, which learns one-step local transition operators; L2 Simulator, which composes them into multi-step, action-conditioned rollouts that respect domain laws; and L3 Evolver, which autonomously revises its own model when predictions fail against new evidence. The second identifies four governing-law regimes: physical, digital, social, and scientific. These regimes determine what constraints a world model must satisfy and where it is most likely to fail. Using this framework, we synthesize over 400 works and summarize more than 100 representative systems spanning model-based reinforcement learning, video generation, web and GUI agents, multi-agent social simulation, and AI-driven scientific discovery. We analyze methods, failure modes, and evaluation practices across level-regime pairs, propose decision-centric evaluation principles and a minimal reproducible evaluation package, and outline architectural guidance, open problems, and governance challenges. The resulting roadmap connects previously isolated communities and charts a path from passive next-step prediction toward world models that can simulate, and ultimately reshape, the environments in which agents operate. Code and resources are available at: this https URL.
科目:人工智能(cs.AI)
Subjects: Artificial Intelligence (cs.AI)