#memory

智能AI None

FinPerMA：LLM 代理的基于理论、基于事件的个性化记忆基准

arXiv:2608.04095v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly used as personalized

memory model personalized

2026-08-06 Ben Wang, Kang Zhou, Lifan Guo, Feng Chen, Chi Zhang

开发者生态 None

美光内存价格五年锁定历史高位

systems Micron locks in historically high memory prices for five years Big buyers agree to deals that will deliver histo

memory and the

2026-06-26 fauigerzigerk

智能AI None

TRUSTMEM：为具有长期记忆的 LLM 代理学习可信赖的记忆整合

25161v1 Announce Type: new Abstract: Large language model (LLM) agents rely on long-term memory to support extended inte

memory and the

2026-06-25 Tianyu Yang, Sudipta Paul, Vijay Srinivasan, Vivek Kulkarni, Srinivas Chappidi

数码硬件 None

Linux 7.2 Slab 的变化包括更多性能优化

The slab memory allocation changes for Linux 7。2 have been merged and continue to see more work around shaves and perfor

and The slab

2026-06-18 Michael Larabel

智能AI None

MemTrace：探究长期记忆中最终准确性的缺失

17328v1 Announce Type: new Abstract: LLM agents increasingly maintain long-term memory of user facts across sessions。

the fact memory

2026-06-17 Xianxuan Long, Zhikai Chen, Shenglai Zeng, Shouren Wang, Kai Guo, Jiliang Tang

开发者生态 None

有一次 x86 模拟器团队发现代码非常糟糕，他们在模拟过程中修复了它

During an exchange of war stories, a colleague of mine told one from back in the days when Windows included a processor

the that code

2026-06-16 paulmooreparks

智能AI None

GRASP：梯度对齐顺序参数传输，实现内存高效的多源学习

arXiv:2606.14900v1 Announce Type: new Abstract: Multi-source transfer learning faces a fundamental scalability bottlenec

source memory and

2026-06-16 Mary Isabelle Wisell, Nicholas Jacobs, Aayush Manandhar, Salimeh Yasaei Sekeh

智能AI None

AI Engram：寻找人工智能中的记忆痕迹

arXiv:2606.14997v1 Announce Type: new Abstract: Memory formation is fundamental to intelligence, yet whether deep neural

and memory engrams

2026-06-16 Jea Kwon, Dong-Kyum Kim, Jiwon Kim, Yonghyun Kim, Woong Kook, Meeyoung Cha

智能AI None

立场：海马外显记忆是 AGI 的基石

11245v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across vario

for memory explicit

2026-06-11 Sangjun Park

智能AI None

记忆工具如何让人工智能模型变得更糟

New research suggests that AI memory systems can degrade model performance and encourage sycophantic tendencies。

New research suggests

2026-06-10 Russell Brandom

数码硬件 None

Linux 发现了影响许多 Arm CPU 的“严重”漏洞补丁

Made public today is CVE-2025-10263 as a "critical" security vulnerability affecting many different Arm CPU cores。

CVE affected memory

2026-06-10 Michael Larabel

智能AI None

基础模型代理中的部署时记忆

arXiv:2606.10062v1 Announce Type: new Abstract: Foundation-model agents are increasingly long-lived systems that remembe

and memory memorization

2026-06-10 Lei (Rachel), Chen, Guilin Zhang, Kai Zhao, Dalmo Cirne, Andy Olsen, Xu Chu, Zeke Miller, Alet Blanken, Amine Anoun, Jerry Ting

智能AI None

OmniMem：用于流式音频视频 LLM 的扰动感知内存压缩

arXiv:2606.07577v1 Announce Type: new Abstract: Audio-visual large language models (LLMs) hold strong promise for long-f

memory the and

2026-06-09 Guangzhi Sun, Yixuan Li, Yudong Yang, Chao Zhang

智能AI None

梦想：更好的记忆力，更有用的 ChatGPT

ChatGPT introduces a new memory system to better remember preferences, keeping context fresh and relevant across convers

ChatGPT introduces new

2026-06-07 OpenAI博客

开发者生态 None

我们应该比模特还累

We should be more tired than the model May 28 2026 Lately, I’ve been feeling like I’m losing control over the code I wri

the and code

2026-05-29 tosh

汽车 None

腾讯混元发布 Hy-Memory：打造记忆力超强的 Agent 第二大脑

IT之家 5 月 28 日消息，腾讯混元宣布正式推出 Hy-Memory。据介绍，这是一个专门为 Openclaw 这类长期协作型 Agent 设计的记忆插件，能真正成为 Agent 的“第二大脑”。官方称，Hy-Memory 用 6 层记

Openclaw Memory Agent

2026-05-28 IT之家

智能AI None

通过长期用户交互个性化体现多模态大语言模型代理

26256v1 Announce Type: new Abstract: Multimodal large language model (MLLM)-based embodied agents have shown strong pote

the interactions memory

2026-05-27 Jeongeun Lee, Chanyoung Park, Dongha Lee

智能AI None

代理内存是数据库吗？重新思考长期人工智能代理内存的数据基础

26252v1 Announce Type: new Abstract: Long-running AI agents need persistent memory。Memory supports learning across sessi

memory the and

2026-05-27 Abdelghny Orogat, Essam Mansour

开发者生态 None

特工记忆：解剖

every agent memory library uses the same words: episodic , semantic , sometimes procedural。they’re cognitive science’s v

the memory and

2026-05-27 brgsk

开发者生态 None

Microsoft 6502 BASIC 现已开源 (2025)

May 19 • 4 min read Introducing STATE-Bench: A benchmark for AI agent memory STATE-Bench is an open-source, memory-agnos

STATE Bench benchmark

2026-05-24 GTP