This work proposes StateMem, a single-state residual memory framework for VLA policies that uses prediction error to update a persistent memory token through low-rank residuals and to adaptively route cached prefixes.
Abstract
Memory-dependent robotic manipulation often requires later actions to use information from earlier interactions. Existing vision-language-action (VLA) policies primarily rely on current observations, limiting historical information retention. Memory-augmented VLAs, such as MemoryVLA, address this limitation with external memory banks but require explicit storage and retrieval. To address these limitations, we propose StateMem, a single-state residual memory framework for VLA policies that uses prediction error to update a persistent memory token through low-rank residuals and to adaptively route cached prefixes. A training-free controller adjusts the routing threshold online, while fast correction compensates for stale prefix features during cache reuse. We evaluate StateMem on LIBERO, RoboMemArena, and real-world manipulation tasks. On LIBERO, StateMem achieves an average success rate of 97.6% and reduces the average VLM prefix refresh rate by 20.25% relative to full refresh. In the Occlusion category of RoboMemArena, StateMem achieves the best performance among single-VLA methods, reaching 21.8% Task Success Rate (TSR) and 44.3% Cumulative Success Rate (CSR). Across six real-world manipulation tasks, it achieves +21% in average success rate.
SimpleMemVLA, a VLA without a dedicated memory module that uses the backbone's native video context directly as memory, achieves state-of-the-art results on four memory benchmarks without loss on general-purpose control, and with the same backbone and training setup it outperforms retrieval, compression and recurrent-s...
C. Yin, Wang Xu, Jun-Peng Yang et al.· 4 citations
Findings support MemBodied as a practical alternative to expanding the policy context for history-dependent manipulation, 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 th...
Tej Deep Pala, N. Majumder, Bryce Goh et al.· arXiv.org· 1 citation
Vision-language-action (VLA) models have driven rapid progress in robotic manipulation, demonstrating strong fine-grained control and promising performance on long-horizon tasks. However, many existing VLAs lack explicit access to interaction history, making them vulnerable to perceptual aliasing: similar current obser...
Ya-Xin Zhao, Dian-Ye Huang, Chen-Wei Wang et al.· 0 citations
MEMOBench is presented, a benchmark for process level memory evaluation in robotic manipulation and provides a diagnostic evaluation suite and training supervision for memory grounded robotic policies.
Hai-Yang Sun, Hao-Xiao Wang, Jun-Ming Chen et al.· 0 citations
HyMeS, a hybrid learning framework that leverages the reasoning and memory-management capabilities of coding agents to steer a Markovian VLA for memory-dependent manipulation, is proposed, enabling data-efficient compositional generalization.
Yun-Hao Zhao, Zhen-Yang Ni, Haoyang Chen et al.· 0 citations
D$^2$-VLA is presented, which combines dual memory and dual-frequency control at the KV-cache interface of a pretrained VLA, which uses block-wise causal KV caching to encode observations incrementally and constructs separate historical KV read views for the VLM and action expert.
Zi-Jian Ye, Chen Wei, Wei Huang et al.· arXiv.org· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 9, 2026