arXiv AI
Simple Agentic Memory for Generalist Robot Policies
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 24
MemBodied: Recurrent Associative Memory for Vision-Language-Action Models
MemBodied introduces a fixed‑size episodic memory for Vision‑Language‑Action models, comprising an associative state that tracks interactions across policy calls and an episode anchor that stores a compact representation of the initial scene. By conditioning action generation on these memory components instead of raw past observations, MemBodied reduces context bloat and inference latency. In five memory‑dependent RMBench tasks, it outperforms stateless and vanilla recurrent policies by significant margins, and achieves a 90.6% success rate on the LIBERO‑Long suite, improving over the baseline by 5.4%.
arXiv AI
Jun 8
Chameleon: Control-Indexed Prospective Memory for Visuomotor Manipulation
arXiv:2603. 24576v2 Announce Type: replace-cross Abstract: Robots often observe information that determines a future action long before that action is executed.
arXiv Machine Learning
Sep 22
StateMem: Single-State Residual Memory with Adaptive Inference for Vision-Language-Action Policies
arXiv:2609.22684v1 Announce Type: cross Abstract: Memory-dependent robotic manipulation often requires later actions to use information from earlier interactions. Existing vision-language-action (VLA...
arXiv AI
Sep 10
MEMOBench: A Process Level Memory Benchmark for Robotic Manipulation
arXiv:2609.07047v1 Announce Type: cross Abstract: Robotic manipulation often requires acting on information that is no longer visible, yet Vision-Language-Action policies are usually evaluated when t...
Hugging Face Trending Papers
Sep 10
2AM: Grounding Agent-Side Memory as Guidance for Steerable Action Models in Long-Horizon Manipulation
The paper introduces 2AM, a system that keeps task memory solely within a multimodal Agent while using a single RGB‑based, stateless Action Model to execute motions. By compiling interaction history into subtask language and optional 2D grasp/place/move hints, the Agent steers the Action Model, which is trained to tolerate imperfect guidance through dropout, noise, and jitter. On the LIBERO‑Mem benchmark, 2AM achieves 76.3% average completion without depth, geometry, or planners, vastly outperforming the best baseline.
arXiv AI
Jul 29
RoboMME-Interference: Benchmarking Robot Memory Under Interference
arXiv:2606. 22338v2 Announce Type: replace-cross Abstract: Robots deployed in realistic settings will accumulate experience across many sessions and tasks over their deployment.