提出多尺度世界模型框架，让智能体在变化环境中更灵活地推理与学习。
Multi-scale Mixture of World Models for Embodied Agents in Evolving Environments
- 通过经验距离判断尺度，分两阶段路由选择合适的世界模型。
- 低尺度知识快速更新，高尺度抽象长期保留，提升适应性。
- 适用于需要持续学习的机器人、自动驾驶等动态场景。
在不断变化的环境中，具身智能体需要多尺度推理和知识适应能力。我们发现将专家混合（MoE）应用于该场景存在两个挑战：路由机制缺乏显式的尺度概念，无法在特定尺度上进行精准更新；统一的更新策略难以应对不同尺度知识过时速度的差异。为此，我们提出MuSix框架，通过感知尺度的世界模型混合与演化来解决上述问题。其采用两阶段路由机制，基于经验距离（受构念水平理论启发）映射到连续尺度空间权重，再由各尺度基路由器选择对应世界模型。在适应方面，引入依赖尺度的遗忘率，使低尺度知识快速刷新而高尺度抽象得以保留，并通过门控跨尺度传输维持层级一致性。在EmbodiedBench和HAZARD上的实验表明，MuSix在多尺度推理和动态适应性能上优于现有最优基线。
原文摘要 · Abstract (English)
Embodied agents operating in the real world require multi-scale reasoning and knowledge adaptation as conditions change. We identify two challenges in applying Mixture of Experts (MoE) to this setting: routing lacks an explicit notion of scale, preventing targeted updates at specific scales, and a uniform update policy cannot accommodate the different rates at which knowledge at each scale becomes outdated. We present MuSix, a framework that addresses both challenges through scale-aware world model mixture and evolution. A two-stage routing mechanism grounds scale selection in experiential distance, a measure of situational novelty inspired by Construal Level Theory: a meta-router first maps this quantity to a weight over continuous scale space, then per-scale base routers select world models within the identified scale. For adaptation, scale-dependent forgetting rates allow low-scale knowledge to refresh rapidly while high-scale abstractions persist, and gated inter-scale transfer maintains coherence across the hierarchy. Experiments on EmbodiedBench and HAZARD show that MuSix improves over state-of-the-art baselines on multi-scale reasoning and dynamic adaptation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。