AnyGoal 基准发布：测试世界模型在专家轨迹之外的泛化能力
AnyGoal: On World Model Generalization Beyond Expert Rollouts
arXiv 上新出的 AnyGoal 基准，专门考世界模型没见过的状态动作组合，多个模型家族测试都翻车，做 world model 研究的可以看看
AnyGoal 是一个由目标偏移任务变体构成的世界模型基准，配套开源了评估库。基准基于常用的世界模型环境构建，任务中的单个状态因子和动作都保持在训练分布内，但它们的新组合在专家轨迹中代表性不足。跨多个环境和多个世界模型家族的测试显示，现有模型在这种状态与动作重组上持续失败。论文还从动力学、表征、交互方式和评估指标多个维度分析了模型在哪里能泛化、哪里仍存在目标偏移预测与规划的挑战。
AnyGoal: On World Model Generalization Beyond Expert Rollouts
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.