arXiv:2606. 02775v1 Announce Type: new Abstract: The KV-cache is the right memory for datacenters but the wrong memory for robots.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2603. 24576v2 Announce Type: replace-cross Abstract: Robots often observe information that determines a future action long before that action is executed.
arXiv:2607. 08032v1 Announce Type: new Abstract: Large language models, and the agents built on them, spend an ever-growing share of their compute and memory on remembering: caching attention keys and values, carrying long prompts, maintaining recurrent state, and storing what happened in previous turns and sessions.
arXiv:2606. 20537v1 Announce Type: new Abstract: Mainstream LLM serving systems reuse prefix work mainly through paged or radix key-value (KV) caches.
arXiv:2607. 10350v1 Announce Type: new Abstract: Recent VLM and VLA systems have improved robotic perception and action prediction, yet long-horizon embodied agents still require a general runtime layer for reasoning, memory, tool use, verification, and cross-embodiment execution.
arXiv:2607. 08716v1 Announce Type: new Abstract: In long-horizon tasks, decision-relevant state is often scattered across an expanding trajectory, while the action agent must surface it and act.
arXiv:2606. 09803v1 Announce Type: cross Abstract: We present \textbf{Echo-Memory}, a controlled study of memory mechanisms in action-conditioned world models.