用记忆检索实现可解释的智能体决策，边运行边优化。
Event-Centric World Modeling with Memory-Augmented Retrieval for Embodied Decision-Making
- 将环境建模为语义事件，通过记忆库检索过往经验
- 实时生成动作，动态适应复杂环境变化
- 适合需要透明决策的无人机等智能体应用
在动态环境中，自主智能体需具备高效且可解释的决策能力。为此，我们提出事件-检索-行动（ERA）框架，一种替代传统黑箱模仿学习的可解释决策方法，支持在线优化而无需重新训练。环境被表示为结构化的语义事件，并编码为可解释的潜在表示；决策通过从事件-动作对知识库中检索相关过往经验生成。最终动作通过加权聚合检索到的行为获得，确保决策过程透明且物理一致。在无人机导航任务中的实验表明，该框架具备实时性能，在动态环境中展现出自适应行为，验证了其在具身决策场景中的有效性。
原文摘要 · Abstract (English)
Autonomous agents operating in dynamic environments increasingly demand decision-making systems that are both efficient and interpretable. Hence we propose the Event-Retrieve-Action (ERA) framework, an alternative formulation for embodied decision-making that bridges the gap between black-box imitation and interpretable memory retrieval while enabling online refinement without retraining. The environment is represented as structured semantic events encoded into an interpretable latent representation, and decisions are generated by retrieving relevant prior experiences from a knowledge bank of event-action pairs. Final actions are produced through weighted aggregation of retrieved maneuvers, enabling transparent and physically consistent decision-making. Experiments in UAV navigation demonstrate real-time performance and adaptive behavior in dynamic environments as a representative embodied decision-making application scenario.
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。