StateMem: Single-State Residual Memory with Adaptive Inference for Vision-Language-Action Policies

2026-09-18

AI Summary

为解决机器人操作中历史信息保留问题，提出StateMem框架，通过预测误差更新记忆令牌并自适应路由缓存前缀，减少刷新率并提高成功率。

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.

Problem

• memory-dependent robotic manipulation
• vision-language-action policies
• historical information retention

Innovation

• single-state residual memory
• adaptive inference
• prediction error
• low-rank residuals
• training-free controller