Persistent Memory for Language Models

Ask about this topic

Overview

Persistent memory lets language models carry useful information across conversations, tasks, or long sequences without repeatedly processing the full history. Approaches include extracting and compressing facts or episodes for lexical, vector, and graph-based retrieval; managing memory through updates, provenance, and forgetting; and adding learned latent, parametric, recurrent, or persistent key-value states. Systems are commonly tested on cross-session question answering and personalization benchmarks such as LoCoMo and LongMemEval, as well as long-context reasoning and interactive agent tasks. The central tension is retaining enough faithful, current evidence for reliable reasoning while controlling storage, token, and latency costs—and preventing stale, sensitive, or poisoned memories from shaping answers.

Latest papers

CardsList

272 papers50 papers in the last four weeks, up 67% on the four weeks before. 0.3% of all new papers.

  1. CALM: Conflict-Aware Lifecycle Memory Governance for Long-Horizon Language Agents

    Oct 28, 2026Chang Li, Xianhao Ou, Xinyan Ma +7Persistent Memory for Language ModelsAgent Memory Governance

    Harbin Institute of Technology · Meituan

  2. StateLoop: Persistent State for Looped Transformers

    Oct 26, 2026Feichen Song, Boyi Zeng, He Li +7Persistent Memory for Language ModelsLanguage Modeling

    Shanghai Jiao Tong University · Sun Yat-sen University · Shanghai Innovation Institute

  3. Delta N-gram: Forward-Only Continual Writing into a Language Model's Native N-gram Memory

    Oct 22, 2026Hao WuPersistent Memory for Language ModelsMemory-Augmented Language Models

    Illinois Institute of Technology

  4. Combining Long-Term Memory and LLMs Comes at a High Cost: From Prompt Injection to Persistent Compromise

    Oct 20, 2026Pedro H. Barcha Correia, Matheus Azevedo de Sá, Paulo H. Gomes de Senna +4LLM SecurityPrompt Injection Attacks on LLMs

  5. Disclosure Begets Disclosure: A Self-Reinforcing Privacy Loop in LLM Agents with Persistent Memory

    Oct 20, 2026Masahiro Kaneko, Hiromi Arai, Timothy BaldwinLLM Agent SecurityPrivacy Protection for LLM Agents

    MBZUAI · Third Intelligence · RIKEN AIP

  6. MemT-1.0: Towards Memory-Native Evolution

    Oct 19, 2026Zhiyu Li, Zeyu Zhang, Linyun Liu +71Memory-Augmented Language ModelsPersistent Memory for Language Models

  7. Atoms, Not Knowledge: What Production-Scale Addressed-Memory Writes Deposit

    Oct 18, 2026Wei Gao, Cheng Tian, Duan Yang +1Memory-Augmented Language ModelsPersistent Memory for Language Models

    Shibei Qiyuan AI Technology · Xi’an Jiaotong University

  8. Memory, Know Your PLACE: Governing Lifecycle State and Query-Time Eligibility in Persistent-Memory Agents

    Oct 18, 2026Chen-Fang Hu, Hong-Han Shuai, Woan-Shiuan ChienAgent Memory GovernanceMemory Management for LLM Agents

    Arˆete Honors Program, National Yang Ming Chiao Tung University, Taiwan · Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Taiwan

  9. Persistent Memory and Iterative Improvement in an LLM Agent for Chinese-Character Drawing

    Oct 16, 2026Peilin Wu, Yi-Zhuang YouPersistent Memory for Language ModelsContinual Learning for LLM Agents

    Palo Alto High School · University of California San Diego

  10. SAFE-Mem: Secure Agentic Memory with Fine-Grained Authority and Governance-Aware Retrieval

    Oct 16, 2026Haoming Li, Dingyi Kang, Xu Hu +8Persistent Memory for Language ModelsAgent Memory Poisoning

    The University of Texas at Dallas · Emory University · Virginia Tech +3

  11. Hy-Memory-30B-A3B: Attributed Reinforcement Learning for Long-Term Memory Writing

    Oct 15, 2026Tianxiang Fei, Jiazheng Kang, Mao Zheng +2Memory-Augmented Language ModelsPersistent Memory for Language Models

    Tencent Hunyuan

  12. Memorilla: Latent Semantic Memory for LLMs

    Oct 15, 2026Adibvafa Fallahpour, Parsa Idehpour, Vignesh Kothapalli +4Memory-Augmented Language ModelsPersistent Memory for Language Models

    Stanford University · University of Toronto · Vector Institute +3

  13. From Long Context to Selective Memory:A Survey of Memory-Centric Compression for Large Language Models

    Oct 15, 2026Chaogui GouLLM Context ManagementMemory-Efficient Inference

    USTB

  14. All-in-One Memory: Process-Rewarded Reinforcement Learning for Memory Agents

    Oct 15, 2026Bingbing Wang, Jingjie Lin, Weiming Qiao +2Persistent Memory for Language ModelsMemory-Augmented Language Model Agents

    Harbin Institute of Technology, Shenzhen · The Hong Kong Polytechnic University · Fudan University +1

  15. Memorizing Who, Knowing How: Benchmarking Personal and Procedural Memory for Persistent Assistants

    Oct 14, 2026Maosheng Qin, Qi Zhang, Mingxuan Xia +5Agent MemoryPersistent Memory for Language Models

    Zhejiang University · Ant Group

  16. Reliable Memory from Unstable Growth: Curating Self-Written Agent Playbooks with Randomized Experiments

    Oct 13, 2026Hoang Pham, Cong-Duy Nguyen, Dong Le +2LLM Agent MemoryPersistent Memory for Language Models

    Nanyang Technological University · VinUniversity

  17. AlignPred: Error-Controlled KV Cache Compression via Alignment and Predictive Coding

    Oct 13, 2026Xu Yang, Jiapeng Zhang, Zhiwei Zuo +5KV-Cache CompressionMemory Compression

    Hunan University · Central China Normal University · Tencent

  18. Engram Injection: A Study of Temporal Validity in Parametric Language-Model Memory

    Oct 11, 2026Sam Siavoshian, Omar Ramadan, Amir K. Saeed +2Temporal Reasoning in Language ModelsPersistent Memory for Language Models

  19. What Survives When Activation Steering Is Used as Memory

    Oct 10, 2026Vedant JumlePersistent Memory for Language ModelsMemory-Augmented Language Models

    Delft University of Technology

  20. VitaBench: Memory Lifecycles Beyond Retrieval

    Oct 10, 2026Muquan Yu, Dihan HuMemory Agent BenchmarksAgent Memory Management

    University of Hong Kong · Chinese University of Hong Kong · Cornell University

  21. MemForm: Benchmarking Memory Formation Poisoning in LLM Agents

    Oct 10, 2026Haowen Pan, Pengyang Shao, Yunshan Ma +4Agent Memory PoisoningPersistent Memory for Language Models

    University of Science and Technology of China · National University of Singapore · Singapore Management University

  22. DPPM: Dual-Path Parametric Memory for Personalized Language Models

    Oct 8, 2026Yuhao Chen, Shuochen Liu, Jiayao Shi +7Memory-Augmented Language ModelsPersistent Memory for Language Models

    University of Science and Technology of China · iFLYTEK Research Group

  23. TraceRelay: Attention-Aligned Recurrence over Rolling Traces

    Oct 8, 2026Sungwoo Goo, Hwi-yeol Yun, Sangkeun JungSequence ModelingPersistent Memory for Language Models

    College of Pharmacy, Chungnam National University · Department of Computer Science & Engineering, Chungnam National University

  24. Memory Type Varies: Empowering LLM Agents for Long-Term Memory with Diverse Strategies

    Oct 8, 2026Yi Wen, Derong Xu, Pengyue Jia +8LLM Agent MemoryPersistent Memory for Language Models

    City University of Hong Kong · Huawei Noah’s Ark Lab

  25. What to Admit and How to Present: Governing Persistent Memory in LLM Agents

    Oct 8, 2026Chang Liu, Deliang DingAgent Memory ManagementPersistent Memory for Language Models

    Pazhou Laboratory Guangzhou, China

  26. Real Long-Term Memory for AI: A 50-Million-Token Window That Is Faster and Cheaper Than Recompute

    Oct 7, 2026Sietse SchelpePersistent Memory for Language ModelsKV-Cache Reuse

    Corbenic AI

  27. Cache the Encoder Within:Compact, Reusable Memory across LLM Queries

    Oct 7, 2026Hanzuo Liu, Chunyu Liu, Chaofan Lin +2Persistent Memory for Language ModelsMemory-Augmented Language Models

    Tsinghua University

  28. Towards In-Parameter Memory Augmentation for Large Language Models

    Oct 6, 2026Haoyu Huang, Zhongwei Xie, Jiaxin Bai +6Memory-Augmented Language ModelsPersistent Memory for Language Models

    The Hong Kong University of Science and Technology · Hong Kong Baptist University

  29. Persistent Memory in Multi-Agent LLM Inference: What It Costs, What It Buys, and When You Can Tell

    Oct 6, 2026Hochan Son, Kyungdoe Han, Jaehan Koh +3LLM Inference EfficiencyMulti-Agent LLM Systems

    University of California, Los Angeles · University of Wisconsin · HCLTech America

  30. PERSIST: Who-What-When Memory Across Sessions for Full-Duplex Spoken Dialogue

    Oct 6, 2026Achira Lin, Siyuan Hou, Wenyi Yu +7Conversational MemoryPersistent Memory for Language Models

    Tsinghua University · Huawei Technologies Ltd.