MemBodied：用固定大小情景记忆提升 VLA 模型的历史依赖任务表现
MemBodied: Recurrent Associative Memory for Vision-Language-Action Models
给做机器人策略的人：MemBodied 用固定大小记忆替代越堆越长的上下文，RMBench 上成功率达到无状态策略的 7.81 倍，参数开销还小 10 倍。
论文提出 MemBodied，一种面向 Vision-Language-Action 模型的固定大小情景记忆，由记录策略调用间交互的 associative state 和保存初始场景紧凑表示的 episode anchor 两部分组成。模型在每次策略调用时基于当前输入和记忆组件生成动作，不再直接堆叠过去观测。在 RMBench 的 5 个记忆任务上，MemBodied 平均成功率达到无状态策略的 7.81 倍、朴素循环记忆的 2.98 倍，并以 10 倍更少的新增参数超过最强记忆增强基线 1.3 倍。在完全可观测的 LIBERO-Long 套件上达到 90.6%，比无状态 π0 策略高 5.4%。
MemBodied: Recurrent Associative Memory for Vision-Language-Action Models
Vision-Language-Action models provide a strong foundation for general-purpose robot control, yet a vast majority of policies do not preserve and leverage episode-level information beyond the current observation. This limitation is consequential in history-dependent manipulation tasks that depend on information available only in past observations. Retaining past observations in context can aid in recovering this information, but at the significant cost of ever-growing, bloated context and inference latency. We thus introduce MemBodied, a fixed-size episodic memory with two complementary components: an associative state that records interactions across policy calls and an episode anchor that preserves a compact representation of the initial scene as a reference. At each policy call, the model conditions action generation on the current input and the memory components, rather than directly using past observations. Across five evaluated RMBench tasks requiring memory, MemBodied achieves $7.81\times$ the mean success rate of a stateless policy and $2.98\times$ of vanilla recurrent memory, while outperforming the strongest memory-augmented baseline by $1.3\times$ with $10\times$ fewer added parameters. On the fully observable LIBERO-Long suite, it reached 90.6%, a 5.4% improvement over the stateless $π_0$ policy. These findings support MemBodied as a practical alternative to expanding the policy context for history-dependent manipulation.