arXiv 综述：具身智能中的记忆机制如何支撑长期任务
When the Past Shapes Action: Understanding Embodied Memory
做具身智能或机器人方向的朋友可以看看，这篇综述把记忆相关的架构和基准都整理成框架了，找研究方向挺省事。
这篇 arXiv 综述系统梳理了具身智能中的记忆机制，提出六大记忆需求维度，覆盖世界状态持久化、任务进度跟踪、信念维持和经验学习。作者将现有方法归为八类架构，包括循环状态、快速权重、视觉与符号表征、空间记忆和基于经验的系统。综述还分析了现有基准如何评估依赖记忆的行为，区分真正利用历史信息与一般任务表现，并指出经验选择、变化环境中信念一致性、跨回合知识整合三大开放挑战。
When the Past Shapes Action: Understanding Embodied Memory
Recent advances in generative foundation models have expanded the capabilities of embodied AI, enabling increasingly general navigation, manipulation, and long-horizon task execution. However, effective interaction with dynamic environments requires more than only strong perception and reasoning: agents must act with partial knowledge and retain, retrieve, and update information from past observations, actions, and experiences. This survey examines embodied memory as a mechanism for preserving decision-relevant information beyond the current observation. We organize existing approaches along two complementary dimensions: six fundamental memory requirements, spanning world-state persistence, task progress, belief maintenance, and experiential learning; and eight architectural categories, including recurrent states, fast weights, visual and symbolic representations, spatial memory, and experience-based systems. We analyze their capabilities and limitations, and examine how existing benchmarks evaluate memory-dependent behavior, distinguishing genuine use of historical information from general task performance. Finally, we identify open challenges in selecting relevant experiences, maintaining consistent beliefs in changing environments, and consolidating knowledge across episodes. Our analysis provides a framework for understanding memory as an essential component of reliable, adaptive, and lifelong-horizon embodied intelligence.
