1
DeepSeek Harness插件一夜燃爆GitHub：长期记忆、电子宠物、4399小游戏全来了
DeepSeek Harness插件爆火GitHub，长期记忆、电子宠物、小游戏齐上阵，700+仓库的玩法大赏来了。
大家已经给DeepSeek装上了啥
2
Show HN: Tried some experiments with architecture for Long term memory for LLM
开源MindCache用非平等结构化的长期记忆，让LLM智能体不再被冗长历史淹没。
The main ideas that survived the experimentation are: using four memory types — user, knowledge, episodic, and decision memories, each with different …
3
Controlled Memory Interference in Continual LLM Agents
聚焦LLM智能体长期记忆中的干扰控制，揭示记忆演化的深层机制，为持续学习系统设计提供新视角。
arXiv:2608.07622v1 Announce Type: new Abstract: Long-term memory enables AI agents to maintain continuity across sessions, personalize behavior, and e…
4
Accurate and Efficient Long-Term Memory for LLM Agents
精准高效长期记忆方案，让LLM智能体更聪明更持久
arXiv:2607.16211v1 Announce Type: new Abstract: LLM agents augmented with persistent memory can recall past interactions, but existing systems suffer …
5
6
PVM:Give any LLM long-term memory.No API keys,no GPU,~800 lines Python.
免API、免GPU，800行Python代码让任意LLM拥有随时间自动衰减的长期记忆
PVM: Give any LLM long-term memory. No API keys, no GPU, ~800 lines Python. Every LLM you've ever used is an amnesiac. ChatGPT forgets your name betwe…
7
Show HN: Two-tier-memory – queryable long-term memory for AI coding agents
给AI编程助手装上“数据库式记忆”：索引常驻、长记忆按需查询，不再被整文件扫描拖垮。
Article URL: https://github.com/tadelstein9/two-tier-memory Comments URL: https://news.ycombinator.com/item?id=48790505 Points: 1 # Comments: 0
8
A-TMA: Decoupling State-Aware Memory Failures in Long-Term Agent Memory
长期记忆系统中“幽灵记忆”如何导致状态失效？解读LLM代理事实变化的协调故障
arXiv:2607.01935v1 Announce Type: new Abstract: Long term memory lets LLM agents act as persistent assistants, but user facts change. A useful memory …
9
How Do AI Agents Remember Things Between Conversations?
深入解析AI代理跨会话记忆机制的技术文章，从短期到长期记忆，用实例讲清原理
AI agents do not truly remember like humans do. Instead, they store useful information outside the chat, retrieve it later, and inject it back into th…
10
TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memory
面向LLM智能体的长期记忆整合新方法，用学习机制让记忆更可信可靠。
arXiv:2606.25161v1 Announce Type: new Abstract: Large language model (LLM) agents rely on long-term memory to support extended interactions and person…
11
MEMPROBE: Probing Long-Term Agent Memory via Hidden User-State Recovery
不依赖下游任务的长期记忆评测新方法，直击Agent用户状态恢复能力。
arXiv:2606.24595v1 Announce Type: new Abstract: Long-term memory promises LLM agents that grow more capable across sessions, maintaining an accurate, …
12
AdaMem: Learning What to Remember for Personalized Long-Horizon LLM Agents
长周期LLM智能体如何自主决定该记什么？这项研究给出了自适应记忆新方案。
arXiv:2606.21144v1 Announce Type: cross Abstract: Long-term memory systems for Large Language Model (LLM) agents typically try to \emph{remember every…
13
MemBuilder: Reinforcing LLMs for Long-Term Memory Construction via Attributed Dense Rewards
告别对话失忆，用属性密集奖励让大模型真正记住历史，长期记忆构建有新招了。
arXiv:2601.05488v4 Announce Type: replace Abstract: Maintaining consistency in long-term dialogues remains a fundamental challenge for LLMs, as standa…
14
Turn Your Best AI Conversations Into a Blog — and Give Your Model a Memory That Lasts
把AI对话自动变成博客和知识库，让模型拥有长期记忆，告别每次从零开始。
Turn Your Best AI Conversations Into a Blog — and Give Your Model a Memory That Lasts blogs.city blogifies and wiki-fies the dialogue you already have…
15
Show HN: LLM Memory Solved?
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
16
MemRefine: LLM-Guided Compression for Long-Term Agent Memory
大模型做智能体记忆压缩，用LLM引导算法优化长期存储效率，读这篇就对了。
arXiv:2606.13177v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly expected to operate over long-term interactions, …
17
Ask HN: Temporal Awareness in LLM?
让大模型感知消息间的时间间隔，提升长篇叙事和日记的连贯性——ChatGPT用户提出的实用功能建议。
I have just sent a sort of "feature request" to ChatGPT (but my question is generally applicable to most LLMs). Here is the text, written by ChatGPT i…
18
Infini Memory: Maintainable Topic Documents for Long-Term LLM Agent Memory
提出Infini Memory方法，用可维护主题文档突破LLM Agent长期记忆瓶颈，为持久化知识管理提供新范式。
arXiv:2606.10677v1 Announce Type: new Abstract: Long-term LLM agents need persistent memory that can track changing facts and provide relevant evidenc…
19
REAL: A Reasoning-Enhanced Graph Framework for Long-Term Memory Management of LLMs
提出REAL推理增强图框架，让LLM长期记忆管理更高效、更可靠。
arXiv:2606.10694v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly expected to interact with users over long time horizons.…
20
Eywa: Provenance-Grounded Long-Term Memory for AI Agents
一种基于溯源的长期记忆新框架，让AI Agent跨会话高效检索信息
arXiv:2605.30771v1 Announce Type: new Abstract: AI agents that persist across sessions need memory they can retrieve, audit, update, and erase. Existi…