Nativemem

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 30

All topics

Mem++: Non-Destructive Memory for Long-Term Organizational LLM Agents
Oct 1, 2026Ahmad Yehia, Aly O. Abdelkareem, Islam Ahmed +4Nativemem Large Language Model Agents
The University of Texas at Austin · AIDAChip Inc.
GenMem: Generative Symbolic Memory for Self-Evolving Harness
Sep 28, 2026Xinke Jiang, Tao Feng, Weixuan Xu +7Agentic Memory Nativemem
National Engineering Research Center of Software Engineering, Peking University, Beijing, China · School of Computer Science, Peking University, Beijing, China · Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China +2
AdaRepair-Mem: Adaptive Experience Orchestration for Repository-Level Program Repair
Sep 17, 2026Z. C. Luo, J. C. Guo, W. J. He +10Automated Program Repair Repair
Zhejiang University · Tencent
CapMem: A Benchmark for Caption-Based Episodic Memory in Egocentric Video
Sep 15, 2026Dingli Liang, Yiqiao Xie, Yukai Huang +6Long Video Question Answering Episodic Memory
University College London · Imperial College London · Durham University +4
ConvMem: Convolutional Memory for Long-Context Reasoning
Sep 9, 2026Hongming Zhang, Zhaozhen Gu, Fengshuo Bai +6Efficient Long-Context Inference Large Language Model Memory
Institute of Automation, Chinese Academy of Sciences
MutMem-V2: Cryptographically Authorized Mutation in Persistent Agent Memory Portable Verification and Reproducible Evidence
Sep 1, 2026Walid SaidiOn-Chain Attestations Nativemem
Independent researcher
HitMem: Hierarchical Temporal 3D Memory with Multi-Modal Context-Aware Retrieval for Dynamic Environments
Sep 1, 2026Ruijie Tang, Chenye Zou, Guoquan Wu +3Spatial Memory Nativemem
Institute of Software, Chinese Academy of Sciences (ISCAS), Beijing, China · University of Chinese Academy of Sciences, Beijing, China · Beijing Key Laboratory of Intelligent Software Engineering, China +1
DP-MemView: A Memory Interface for Attribute-Level Transcript Privacy in Long-Term LLM Agents
Aug 4, 2026Jong Wook Kim, Byoungjae Min, Kennedy Edemacu +3Nativemem Peak Memory
Department of Computer Science, Sangmyung University, Seoul, Republic of Korea · College of Staten Island, The City University of New York, New York, NY, USA · Sookmyung Women’s University, Seoul, Republic of Korea +2
UniMem: Complementary Episodic-to-Parametric Memory for Boundary-Agnostic Task Streams
Jul 28, 2026Siyu Xia, Chenheng Zhang, Yanting Wu +8Parametric Memory Episodic Memory
Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, China · State Key Lab of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University +3
Mi-Memory: A Lifecycle Memory Framework for Personal AI
Jul 21, 2026Xule Liu, Hanlin Teng, Chao Li +15Nativemem Artificial Intelligence Systems
Darwin Agent Team
MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations
Jul 14, 2026Xixuan Hao, Zeyu Zhang, Zehao Lin +6Conversational Memory Nativemem
MemTensor (Shanghai) Technology Co., Ltd. · The Hong Kong University of Science and Technology (Guangzhou) · Renmin University of China
OpsMem: Dual-Memory Reasoning with Cross-Memory Resonance for Failure Diagnosis
Jul 13, 2026Yongqian Sun, Rongchen Gao, Yu Luo +6Microservices Nativemem
Nankai University · Huawei Technologies Co., Ltd. · Tsinghua University
NativeMEM: Native Memory Compression for Long-Horizon Robotic Manipulation
Jul 7, 2026Ziye Wang, Modi Shi, Chaojun Ni +5Vision Encoders Nativemem
The University of Hong Kong · Beihang University · Peking University +2
SelfMem: Self-Optimizing Memory for AI Agents
Jul 4, 2026Shu Yang, Junchao Wu, Derek F. Wong +1Self-Improving Agents Semantic Memory
1PRADA Lab, King Abdullah University of Science and Technology · NLP2CT Lab, University of Macau
ConvMemory v3: A Validity Context Layer for Conversational Memory via Target-Conditioned Relation Verification
Jun 25, 2026Taiheng PanConversational Memory Nativemem
School of Computing and Information Systems University of Melbourne
Mem-World: Memory-Augmented Action-Conditioned World Models for Persistent Robot Manipulation
Jun 17, 2026Zirui Zheng, Jiaqian Yu, Xiongfeng Peng +7Efficient World-Action Model Robotic Manipulation
1Dalian University of Technology · 2Samsung R&D Institute China-Beijing (SRCB), China
ConvMemory v2: A Recall-Preserving Top-10 Evidence Reranker for Conversational Memory Retrieval
Jun 9, 2026Taiheng PanConversational Memory Nativemem
School of Computing and Information Systems University of Melbourne
memorywire: A Vendor-Neutral Wire Format for Agent Memory Operations
May 31, 2026Thamilvendhan MunirathinamNativemem Model Context Protocol
Independent Researcher
DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory
May 29, 2026Zhenhao Yang, Xiaoshi Wu, Zhengyao Lv +5Interactive Video Generation Playable Video World Generation
1The University of Hong Kong · *Work done during an internship at Kling Team, Kuaishou Tech. · 2Kling Team, Kuaishou Technology
ElasticMem: Latent Memory as a Learnable Resource for LLM Agents
May 29, 2026Tao Feng, Chongrui Ye, Tianyang Luo +5Large Language Model Agents Nativemem
University of Illinois Urbana-Champaign · Nanyang Technological University
IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference
May 25, 2026Xintong Yang, Hao Gu, Binxing Xu +6Efficient Long-Context Inference Key-Value Cache Eviction
The Hong Kong University of Science and Technology · Zhejiang University
Self-Evolving Multi-Agent Systems via Decentralized Memory
May 21, 2026Guangya Hao, Yunbo Long, Zhuokai ZhaoMulti-Agent Evolution Nativemem
University of Cambridge · University of Chicago
DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Agent Memory
May 21, 2026Jianing Yin, Tan Tang, Yingcai WuLarge Language Model Memory Nativemem
State Key Lab of CAD&CG, Zhejiang University
MemRepair: Hierarchical Memory for Agentic Repository-Level Vulnerability Repair
May 17, 2026Simiao Liu, Li Zhang, Fang Liu +3Automated Program Repair Repository-Level Code Understanding
Beihang University Beijing, China · The University of Hong Kong Hong Kong, China
DimMem: Dimensional Structuring for Efficient Long-Term Agent Memory
May 15, 2026Wentao Qiu, Haotian Hu, Fanyi Wang +2Long-Term Agent Memory Long-Term Memory
1StepOS · 2Xiamen University · 3ShanghaiTech University
SoK: Unlearnability and Unlearning for Model Dememorization
May 12, 2026Mengying Zhang, Derui Wang, Ruoxi Sun +3Exact Unlearning Unlearnable Examples
RMIT University Australia · CSIRO Australia · University of Texas at Dallas USA +1
Mem-W: Latent Memory-Native GUI Agents
May 10, 2026Guibin Zhang, Yaohui Ling, Fanci Meng +2Graphical User Interface Agents Nativemem
LV-NUS Lab, NUS & NTU
MemCompiler: Compile, Don't Inject -- State-Conditioned Memory for Embodied Agents
May 8, 2026Xin Ding, Xinrui Wang, Yifan Yang +9Nativemem Embodied Agents
University of Science and Technology of China · Huazhong University of Science and Technology · Microsoft Research +2
MEMOREPAIR: Barrier-First Cascade Repair in Agentic Memory
May 8, 2026Yang Zhao, Chengxiao Dai, Mengying Kou +1Agentic Memory Nativemem
Membox: Weaving Topic Continuity into Long-Range Memory for LLM Agents
Jan 7, 2026Dehao Tao, Guoliang Ma, Yongfeng Huang +1Nativemem
Tsinghua University · Xinjiang University

Oct 1, 2026, cs.CLJ/K move · Enter open · S save

Mem++: Non-Destructive Memory for Long-Term Organizational LLM Agents

Ahmad Yehia, Aly O. Abdelkareem, Islam Ahmed, Hesham Omran+3

The University of Texas at Austin · AIDAChip Inc.

Nativemem Large Language Model Agents

Open paper AskPDF arXiv

Large Language Model (LLM) agents now take part in organizational work, where many authors record decisions across documents over months. Because a revised decision arrives as a new document rather than an edit, answering a question requires knowing which version held at a given time. However, most memory systems compress the record at write time. By distilling each document into facts, notes or graph edges, these methods fix what can be answered before any question is asked. To address this, we propose Mem++, a non-destructive memory framework shifting from write-time distillation to read-time selection. Mem++ stores every document whole with its date and author, and it calls no generative model at write time. At read time, it retrieves only documents dated up to the time a question asks about and fuses lexical and semantic rankings. Unlike systems that overwrite older versions, Mem++ keeps them and leaves the choice to the answering model. Evaluations on the organizational benchmark OrgMemBench demonstrate that Mem++ surpasses the strongest memory system baseline by 8.0 to 13.1 points across two answering models. With gpt-4.1-mini, it also achieves the best overall score, 2.6 points above RAG. In addition, Mem++ achieves the best average LLM-judge score on LoCoMo and ranks second on LongMemEval-S, behind only its entity-graph variant. Code for benchmark evaluation is available at https://github.com/AIDAChip-Inc/mem-plus-plus.

Momentum

Related topics

Latest papers 30