MemBodied: Recurrent Associative Memory for Vision-Language-Action Models

Published September 24, 2026 · Category: Robotics

Overview

arXiv:2609.28256v1 Announce Type: new Abstract: 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 $\pi_0$ policy. These findings support MemBodied as a practical alternative to expanding the policy context for history-dependent manipulation.

Source

Originally published at arxiv.org.

Related Articles

• Less Language, More Latents: Annotation-Efficient VLAs for Driving
• Task-Prototype Guided Flow Matching for Few-Shot Generalization in Vision-Language Robot Manipulation
• Anchor-Free Hidden-Target Seeking via Certified Self-Calibration under Correlated Odometry