arXiv AI June 17, 2026 By Josef Liyanjun Chen

Memory as a Wasting Asset: Pricing Flash Endurance for Embodied Agents, and the Limits of Doing So

arXiv:2606. 18144v1 Announce Type: new Abstract: A robot's flash endurance is a non-renewable stock: every persisted write spends one of a few thousand program/erase cycles and never refills, yet no fielded robot memory system prices which memories are worth an erase cycle.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

1d ago

Don't Drop the BATON: Long-Horizon Robot Manipulation via Agentic Subtask Exploration and Transition-aware Memory

arXiv:2608. 16889v1 Announce Type: cross Abstract: Long-horizon robot manipulation chains many contact-rich skills into one multi-stage task.

By Bingxin Xu, Yuzhang Shang, Emilio Ferrara

llms agents robotics multimodal benchmarks

arXiv AI

Jun 3

AURA: Action-Gated Memory for Robot Policies at Constant VRAM

arXiv:2606. 02775v1 Announce Type: new Abstract: The KV-cache is the right memory for datacenters but the wrong memory for robots.

By Josef Chen

agents robotics multimodal benchmarks

arXiv AI

Jul 21

Memory in the Loop: In-Process Retrieval as Extended Working Memory for Language Agents

arXiv:2607. 05690v2 Announce Type: replace Abstract: Language agents run a loop - observe, reason, act - but the memory they reason over sits outside it: a store queried at most once per turn.

By Yusuf Khan, Carlo Lipizzi

llms rag agents

arXiv Machine Learning

Jun 25

Forget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memory

arXiv:2606. 25115v1 Announce Type: new Abstract: On-device language-model agents improve by accumulating experience in retrieved memory rather than by updating weights.

By Beining Wu, Zihao Ding, Jun Huang, Yanxiao Zhao

llms agents robotics benchmarks

arXiv AI

Jul 8

Memory in the Loop: In-Process Retrieval as ExtendedWorking Memory for Language Agents

arXiv:2607. 05690v1 Announce Type: new Abstract: Language agents run a loop - observe, reason, act - but the memory they reason over sits outside it: a store queried at most once per turn.

By Yusuf Khan, Carlo Lipizzi

llms rag agents

arXiv AI

Jul 9

Memory Scarcity, Open Models, and the Restructuring of the AI Industry, 2026-2030 -- A quantitative scenario analysis of inference economics, training-cost divergence, and infrastructure solvency

arXiv:2607. 07207v1 Announce Type: cross Abstract: We analyze how four forces restructure the AI industry over 2026-2030: the DRAM/HBM price surge, frontier-capable open-weight models (GLM-5.

By Satoshi Matsuoka

reinforcement-learning efficiency

Related stories

Don't Drop the BATON: Long-Horizon Robot Manipulation via Agentic Subtask Exploration and Transition-aware Memory

AURA: Action-Gated Memory for Robot Policies at Constant VRAM

Memory in the Loop: In-Process Retrieval as Extended Working Memory for Language Agents

Forget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memory

Memory in the Loop: In-Process Retrieval as ExtendedWorking Memory for Language Agents

Memory Scarcity, Open Models, and the Restructuring of the AI Industry, 2026-2030 -- A quantitative scenario analysis of inference economics, training-cost divergence, and infrastructure solvency