AI 学到的世界规则，换个目标就失灵
AI 智能体靠「世界模型」在脑子里模拟行动后果，再挑最优路线。但新研究发现：把训练时见过的状态和动作重新组合成新任务，当前主流世界模型几乎全部翻车——不是没见过这些零件，而是不会把它们拼起来。研究者为此做了 AnyGoal 基准，把熟悉的目标位置挪到新组合上，结果模型预测和规划双双崩坏。这不是数据不够，而是模型根本没学会「规则」，只背下了见过的场景。它不是你明天能用上的东西，但它划了一条线：现在 AI 的「世界理解」，离真懂还差一个组合泛化。
📄 原文摘要(英文)
The goal of a world model is to capture the dynamics of an environment. This has the great appeal that it allows agents to plan and simulate a course of actions with the help of a world model. For these uses to be reliable, however, the learned dynamics must behave well beyond the specific state-action combinations observed in expert rollouts. Despite this, the relationship between data coverage, dynamics generalization, and downstream planning performance remains underexplored. We study this relationship through the lens of compositional generalization: can a world model recombine familiar state and action factors into valid dynamics? To answer this, we introduce AnyGoal, a benchmark of goal-shifted task variants built from widely used world-model environments, together with an open-source library. Each task is designed to be within reach of a world model that has learned the underlying dynamics: individual state factors and actions remain within their training support, but their combinations are underrepresented in expert trajectories. Across multiple environments and world model families, we find that current models consistently exhibit failures under these recombinations. By examining dynamics and representation failures across model families, interaction regimes, and evaluation metrics, we study where current world models generalize and where challenges remain for goal-shifted prediction and planning. Together, this framework, benchmark, and analysis provide a basis for evaluating progress toward world models that generalize to new planning tasks.