具身记忆如何塑造智能体行动：一篇系统性综述
When the Past Shapes Action: Understanding Embodied Memory
AI 导读
一篇 arXiv 综述系统梳理具身 AI 中的记忆机制，即智能体在当前观测之外保留决策相关信息的能力。综述沿两个维度组织现有方法：六项基本记忆需求（世界状态持久化、任务进度、信念维持与经验学习等）和八类架构（循环状态、fast weights、视觉与符号表示、空间记忆、经验系统等），并分析各基准如何区分真实的历史信息利用与一般任务表现。
正文 · 原文
Abstract: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.
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.41688 [cs.RO] |
| (or arXiv:2610.41688v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.41688 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Börje F. Karlsson [view email]
[v1]
Fri, 30 Oct 2026 12:52:37 UTC (3,532 KB)
来源：arXiv cs.AI · arxiv.org