1
BYOKs for an LLM with a Brain
当LLM装上“大脑”，BYOK模式开启个性化智能新玩法，值得一看
Article URL: https://alicebraincore.web.app Comments URL: https://news.ycombinator.com/item?id=49357139 Points: 1 # Comments: 0
2
LLMs Are Not Good Strategists, Yet Memory-Enhanced Agency Boosts Reasoning
LLM策略短板明显，记忆增强代理却能让推理能力飙升，值得关注。
arXiv:2608.12626v1 Announce Type: cross Abstract: Strategic reasoning in Large Language Models (LLMs) within long-horizon environments is often limite…
3
TF-Engram: A Train-Free Engram with SSD-Backed Memory for Large Language Models
无需额外训练的SSD记忆增强方案，让LLM轻松扩展长上下文记忆。
arXiv:2607.07388v1 Announce Type: cross Abstract: Large Language Models (LLMs) store factual knowledge and domain-specific patterns implicitly in dens…
4
MemPose: Category-level Object Pose Estimation with Memory
记忆增强的类别级物体位姿估计新方法，ECCV 2026 论文带你突破遮挡与对称难题
arXiv:2607.04930v1 Announce Type: cross Abstract: In the pursuit of robust and generalizable category-level object pose estimation, most existing meth…
5
Selective Memory Retention for Long-Horizon LLM Agents
ICML 2026收录，揭秘LLM智能体如何在长期任务中精选记忆、提升性能。
arXiv:2606.29178v1 Announce Type: cross Abstract: When does retention matter for memory-augmented LLM agents? We study this with TraceRetain, a lightw…
6
AI Has Amnesia. Here's Every System Built to Fix It
AI失忆症不再是难题，这篇全方位盘点所有修复方案，一网打尽各大系统与技术。
Article URL: https://medium.com/@alanayalag/your-ai-has-amnesia-heres-every-system-built-to-fix-it-ad7dee117a75 Comments URL: https://news.ycombinator…
7
Tired of AI amnesia, I built a 3-Tier infinite memory LLM in 1 week
厌倦AI失忆？开发者一周内用3层无限记忆架构解决了大模型遗忘难题。
Article URL: https://dl-chat-49232436682.asia-northeast3.run.app/ Comments URL: https://news.ycombinator.com/item?id=48496730 Points: 2 # Comments: 1
8
Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents
解决长时域LLM智能体记忆中继质量退化难题，提出元认知记忆策略优化新方法
arXiv:2605.30159v1 Announce Type: new Abstract: Memory-augmented LLM agents tackle complex long-horizon tasks by recursively summarizing interaction t…
9
Shopping Companion: A Memory-Augmented LLM Agent for Real-World E-Commerce Tasks
将记忆机制融入大语言模型，打造能处理真实长周期电商购物任务的智能体，解决偏好跟踪与落地难题。
arXiv:2603.14864v2 Announce Type: replace Abstract: In e-commerce, LLM agents show promise for shopping tasks such as recommendations, budget manageme…
10
Evo-Attacker: Memory-Augmented Reinforcement Learning for Long-Horizon Tool Attacks on LLM-MAS
用记忆增强强化学习，让AI攻击更擅长长周期工具操纵，直指LLM多智能体系统的安全命门。
arXiv:2605.25389v1 Announce Type: cross Abstract: While Large Language Model-based Multi-Agent Systems (LLM-MAS) demonstrate remarkable capabilities i…
11
SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
ICML 2026收录：为LLM智能体设计的分层记忆增强安全护栏，提升复杂场景下的行为可控性。
arXiv:2605.05704v2 Announce Type: replace-cross Abstract: Recent advances in foundation models have transformed LLMs from passive conversational syste…
12
What Training Data Teaches RL Memory Agents: An Empirical Study of Curriculum Effects in Memory-Augmented QA
揭秘训练数据对RL记忆体的课程效应，实证研究记忆增强QA中的性能提升关键。
arXiv:2605.23067v1 Announce Type: new Abstract: Reinforcement learning (RL) has emerged as a viable recipe for training LLM agents to reason over exte…
13
Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
破解多会话强化学习中记忆增强LLM智能体的公平信用分配难题，来自最新学术论文
arXiv:2605.21768v1 Announce Type: new Abstract: Memory-augmented LLM agents enable interactions that extend beyond finite context windows by storing, …
14
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
揭示记忆增强的LLM代理在长期使用中面临的安全风险，提醒关注AI系统持续记忆带来的新威胁。
arXiv:2605.17830v1 Announce Type: cross Abstract: Safety evaluations of memory-equipped LLM agents typically measure within-task safety: whether an ag…
15
Long Context Modeling with Ranked Memory-Augmented Retrieval
用排序记忆增强检索解决长上下文建模，突破大模型上下文窗口限制。
arXiv:2503.14800v3 Announce Type: replace-cross Abstract: Effective long-term memory management is crucial for language models handling extended conte…
16
State Contamination in Memory-Augmented LLM Agents
揭示LLM代理因记忆摘要隐藏毒性上下文的安全漏洞，记忆污染研究新发现
arXiv:2605.16746v1 Announce Type: cross Abstract: LLM agents increasingly rely on persistent state, including transcripts, summaries, retrieved contex…
17
AMARIS: A Memory-Augmented Rubric Improvement System for Rubric-Based Reinforcement Learning
提出记忆增强的评分标准改进系统，提升基于评分标准的强化学习效果。
arXiv:2605.18592v1 Announce Type: new Abstract: Rubric-based reward shaping is an effective method for fine-tuning LLMs via RL, where structured rubri…
18
Memory-Augmented Query Intent Understanding for Efficient Chat-based Image Retrieval
该工具基于多轮对话理解用户意图，实现高效图像检索，创新融合记忆增强机制
arXiv:2605.17365v1 Announce Type: new Abstract: Different from traditional text-to-image retrieval tasks, chat-based image retrieval allows the human-…
19
Agentic Recommender System with Hierarchical Belief-State Memory
将推荐建模为部分可观测问题，MARS用分层信念状态记忆分离短期信号与稳定偏好，首次为记忆演化提供完整生命周期——推荐系统的记忆终于不再是一团乱麻。
arXiv:2605.14401v1 Announce Type: cross Abstract: Memory-augmented LLM agents have advanced personalized recommendation, yet existing approaches unive…
20
SE-GA: Memory-Augmented Self-Evolution for GUI Agents
请问您是想推荐这篇论文中提到的“SE-GA”框架，还是需要我帮您推荐其他在线工具？SE-GA是一个学术研究框架，并非可直接使用的在线工具。请确认并提供工具的网址或名称。
arXiv:2605.16883v1 Announce Type: new Abstract: Autonomous Graphical User Interface (GUI) agents often struggle with multi-step tasks due to constrain…