让大模型像人类一样学习记忆管理，将文件系统操作变为可训练的认知技能
arXiv:2607.01224v1 Announce Type: new Abstract: Memory expertise is a learned skill: knowing what to encode, when to retrieve, and how to organize kno…
neuron-db为LLM打造持久化记忆，突破上下文窗口限制，让模型用3D可视化召回事实，开源方案或成记忆难题解法。
Article URL: https://github.com/gary23w/neuron-db Comments URL: https://news.ycombinator.com/item?id=48527346 Points: 1 # Comments: 0
打破用户记忆统一评分迷思，揭示LLM个性化失败的三维诊断框架。
arXiv:2606.11712v1 Announce Type: cross Abstract: User-side memory in LLMs is typically scored as a single "personalization" capability: given a user'…
终结LLM上下文泄露：100%精度记忆，告别向量搜索的10%低效。
Article URL: https://tenureai.dev/ Comments URL: https://news.ycombinator.com/item?id=48409678 Points: 4 # Comments: 1
向量搜索无法胜任LLM长期记忆，这个新基准测试揭示其关键缺陷与应对方向。
Article URL: https://github.com/tenurehq/precisionMemBench Comments URL: https://news.ycombinator.com/item?id=48404090 Points: 1 # Comments: 0
盘点AI Agent记忆方案，10+开源项目精选，从mem0到Hindsight，star数从15k到57k，开发者选型必备。
Article URL: https://grigio.org/w/ Comments URL: https://news.ycombinator.com/item?id=48382280 Points: 1 # Comments: 0
单64KB超向量承载无限LLM记忆，支持离线可验证与GDPR遗忘，AI代理记忆的突破性方案。
Article URL: https://github.com/OpenAgentic-Labs/echoform-ghost-memory Comments URL: https://news.ycombinator.com/item?id=48192963 Points: 1 # Comment…
现有LLM记忆评估靠最终准确率，但会掩盖关键失败模式，本文提出新视角
arXiv:2605.15384v1 Announce Type: cross Abstract: Memory plays a central role in enabling large language models (LLMs) to operate over sequential task…