These results support a state-based view of robot memory: effective memory for control is not simply retained visual history, but compact task-relevant state derived from the interaction history.
Abstract
Visual-memory systems commonly retain or compress past observations. Robot control additionally requires interaction-derived state that no individual frame may explicitly represent, such as persistent identity relations, accumulated progress, or ordered procedures. We introduce Simple Agentic Robot Memory (SimpleARM), a training-free memory layer for frozen generalist robot policies. From the task instruction, SimpleARM specifies what to monitor; frozen perceptual tools maintain compact typed state online; structured access retrieves that state only when a proposed subgoal depends on history; and current-view grounding resolves recalled entities before execution. We evaluate SimpleARM on RoboMME, a benchmark of memory-dependent robot manipulation tasks that require history information no longer available in the current observation. Across all 16 tasks and three policy seeds, SimpleARM achieves 67.17% mean success, compared with 44.51% for the strongest non-oracle baseline. Matched ablations show mechanism specificity: removing relation, reference, progress, or route state produces large losses where the affected state is retrieved for control, while largely sparing other tasks. These results support a state-based view of robot memory: effective memory for control is not simply retained visual history, but compact task-relevant state derived from the interaction history.
Comparisons within ReCAT show that the observation encoder and every-block memory conditioning are needed for this performance, and that update rules developed for efficient sequence modeling behave differently as robot memory: additive updates have the highest observed success on counting and timing, and delta-rule up...
Pankhuri Vanjani, M. Hatab, Can Mizrakli et al.· arXiv.org· 0 citations
Results show that explicit concepts provide a reusable and extensible memory interface for robot control and motivate ECoMEM, which represents task-relevant history with a reusable library of grounded concepts.
Yi-Ze Liu, Ke Wang, Mac Schwager et al.· 0 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) policies commonly place a multi-billion-parameter model inside the feedback loop, repeatedly recomputing task context whenever they predict a new action chunk. Yet task understanding changes far more slowly than the robot state. We introduce Fast-VLA, which invokes a frozen 4B VLM once per...
Ke-Hong Gong, Guan-Ling Hou, Xiao-Xu Zheng et al.· 0 citations
Generalist robot policies and language-model agents provide complementary capabilities, but completing a task also requires adapting their use to the consequences of physical interaction. We study execution as a locus of adaptation: feedback guides the current action and supplies evidence for revising subsequent decisi...
He-Yang Yu, Hao-Min Li, Si-Hang Li et al.· 1 citation
We use a frozen frontier vision-language model, GPT-6-Astra, directly as the robot policy on RoboMME, a benchmark of 16 memory-dependent manipulation tasks spanning temporal, spatial, object, and procedural memory. The model keeps the whole episode in context and outputs every end-effector waypoint and gripper command,...
Jack B. Jedlicki, Amish Sethi, Heng Yang· 1 citation· ⚡1
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduJul 30, 2026
From feet to fingertips — we are teaching robots intelligent whole-body control, fine dexterity, and teamwork to complete a broad range of complex tasks.