Memory Consolidation

Ask about this topic

Overview

Memory consolidation studies how learners turn transient experiences into durable knowledge while balancing adaptation, retention, storage, and access. Approaches include sleep-like replay and fast/slow synaptic dynamics in continual learning, and episodic-to-semantic transfer, graph or topic organization, and learned compression in language-agent memory. Work is evaluated in settings such as Split-MNIST and Split-CIFAR continual learning, and long-term recall benchmarks including LongMemEval and LoCoMo. Consolidation can save capacity and improve generalization, but may discard useful episodes, provenance, or temporal cues, leaving an open tradeoff between compact summaries and preserving original evidence.

Latest papers

CardsList

34 papers4 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

  1. PreCoMem: Predictive Cognitive Memory for Self-Evolving Long-Term Dialogue Agents

    Oct 21, 2026Jian Zhong, Zeyu Liu, Pingchuan Cao +8Memory Management for LLM AgentsLong-Term Conversational Memory

    Nankai University · Tsinghua University · Huazhong University of Science and Technology +2

  2. Co2In: a Bi-level Memory Incremental Learning Framework with Knowledge Encoding, Consolidation, and Integration

    Oct 15, 2026Wenju Sun, Qingyong Li, Boyang Li +4Task-Incremental LearningIncremental Learning

    Key Laboratory of Big Data & Artificial Intelligence in Transportation (Ministry of Education), Beijing Jiaotong University, Beijing, China, 100044. · College of Computing and Data Science, Nanyang Technological University, Singapore, 639798. · Fujian Key Laboratory of Big Data Application and Intellectualization for Tea Industry, Wuyi University, Fujian, China, 354300.

  3. Use and Disuse: Intent-Structured Experience Consolidation for Memory and Learning in LLM Agents

    Oct 8, 2026Xiangyi Zeng, Baihang Liu, Xutong Wang +3Memory-Augmented Language Model AgentsContinual Learning for LLM Agents

    Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China · School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China

  4. Memory Consolidation Flattens the Temporal Shape of User Facts

    Sep 29, 2026Sugam Panthi, Muhaiminul Yeamin, Siyan Luo +1Long-Term Conversational MemoryMemory Consolidation

    AIMS Lab, The University of Southern Mississippi

  5. ROAM: Robust Organization of Atomic Memories for Agents through Semantic Relations

    Sep 9, 2026Jianjie Zheng, Peng Lai, Sijie Cheng +3LLM Agent MemoryPersistent Memory for Language Models

    Southern University of Science and Technology · Tsinghua University · Deepexi Technology Co. Ltd.

  6. In Two Minds about Lifelong Learning: Exploring Hemispheric Redundancy and Specialisation in Neural Models

    Aug 20, 2026Benjamin Smith, Levin Kuhlmann, Kaushik Roy +1Online Continual LearningBiologically Plausible Learning

    Data Science and AI, Monash University, Wellington Road, Clayton, 3800, Victoria, Australia · CSIRO Robotics, CSIRO, Australia · Cerenaut, Victoria, Australia

  7. Consolidator: Learning Persistent Routed Memory Across Context Boundaries

    Aug 12, 2026Sungwoo Goo, Hwi-yeol Yun, Sangkeun JungMemory-Augmented Neural NetworksPersistent Memory for Language Models

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

  8. PMMC: Prospective Multimodal Memory Compilation for Long-Term LVLM Agents

    Aug 2, 2026Jingyu Sun, Yan Lin, Yuyang Xue +10Memory-Augmented VLMsMultimodal Memory

    The University of Manchester · The University of Newcastle · The University of Edinburgh +5

  9. UniMem: Complementary Episodic-to-Parametric Memory for Boundary-Agnostic Task Streams

    Jul 28, 2026Siyu Xia, Chenheng Zhang, Yanting Wu +8Continual Learning for LLM AgentsOnline Continual Learning

    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

  10. Retain or Consolidate? Budget-Dependent Operator Selection for Language Agent Memory

    Jul 20, 2026Qingcan Kang, Mingyang Liu, Shixiong Kai +5LLM Agent MemoryPersistent Memory for Language Models

    Huawei Noah’s Ark Lab · Department of Computer Science, City University of Hong Kong

  11. Intrinsic-Noise Consolidation: A Doob-Barrier-Conditioned Diffusion Turns Analog Device Noise into a Continual-Learning Resource

    Jul 8, 2026Gunner Levi HoweContinual LearningStability-Plasticity Dilemma

  12. Episodic-to-Semantic Consolidation Without Identity Drift

    Jul 2, 2026Xue Qin, Simin Luan, Cong Yang +1AI Agent GovernanceMemory Consolidation

    aSchool of Software, Harbin Institute of Technology, Harbin, China · bSchool of Computer Science and Technology, Harbin Institute of Technology, Harbin, China · cSchool of Future Science and Engineering, Soochow University, Suzhou, China

  13. EVAF: A Test-Retest Protocol for Selective Parametric Consolidation

    Jun 29, 2026Haoliang HanAgent MemoryContinual Learning for LLM Agents

    Institute of Biomedical Strategy, China Pharmaceutical University

  14. Memory Depth, Not Memory Access: Selective Parametric Consolidation for Long-Running Language Agents

    Jun 25, 2026Haoliang HanAgent MemoryContinual Learning for LLM Agents

    Institute of Biomedical Strategy, China Pharmaceutical University

  15. Learning What to Remember: A Cognitively Grounded Multi-Factor Value Model for Agentic Memory

    Jun 11, 2026Zhibao Chen, Qian ChengLLM Agent MemoryPersistent Memory for Language Models

    Huatai Securities, Nanjing, China

  16. Infini Memory: Maintainable Topic Documents for Long-Term LLM Agent Memory

    Jun 9, 2026Suozhao Ji, Baodong Wu, Zehao Wang +8Agentic RAGPersistent Memory for Language Models

    1Infinigence AI · 2Tsinghua University · 3Shanghai Jiaotong University

  17. Not Just After One: Sleep-Inspired Replay Prevents Catastrophic Forgetting After Sequential Tasks

    Jun 7, 2026Anthony Bazhenov, Jean Erik Delanois, Giri P. KrishnanReplay-Based Continual LearningMemory Consolidation

    Khoury College of Computer Sciences, Northeastern University, Boston, MA · Department of Medicine, University of California, San Diego, La Jolla, CA, USA · ARTISAN, Georgia Institute of Technology, Atlanta, GA USA

  18. DELTAMEM: Incremental Experience Memory for LLM Agents via Residual Trees

    Jun 2, 2026Haoran Tan, Zeyu Zhang, Zhicheng Cao +2Continual Learning for LLM AgentsLLM Agent Memory

    Gaoling School of Artificial, Renmin University of China, Beijing, China · Beijing Key Laboratory of Research on Large Models and Intelligent Governance · Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE +1

  19. Don't Ask the LLM to Track Freshness: A Deterministic Recipe for Memory Conflict Resolution

    May 31, 2026Vikas Reddy, Sumanth ChallaramLLM Agent MemoryAI Agent Benchmarks

  20. Balancing Plasticity and Stability with Fast and Slow Successor Features

    May 25, 2026Raymond Chua, Doina Precup, Blake RichardsSequential Decision MakingNon-Stationary RL

    School of Computer Science, McGill University, Montr´eal, Canada · Mila - Quebec Artificial Intelligence Institute, Montr´eal, QC, Canada · CIFAR Learning in Machines and Brains +3

  21. Short-Term-to-Long-Term Memory Transfer for Knowledge Graphs under Partial Observability

    May 21, 2026Taewoon Kim, Vincent François-Lavet, Michael CochezPartially Observable RLQ-Learning

    1HumemAI · 2Vrije Universiteit Amsterdam · 3ELLIS Institute Finland & Abo Akademi University

  22. Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents

    May 20, 2026Chongrui Ye, Yuxiang Liu, Yu Wang +5Continual Learning for LLM AgentsContinual Learning

    University of Illinois Urbana-Champaign · University of California San Diego

  23. Episodic-Semantic Memory Architecture for Long-Horizon Scientific Agents

    May 17, 2026Nikola MilosevicLLM Agent MemoryLong-Horizon LLM Agents

    Serbian Institute for Artificial Intelligence Research and Development, Fruskogorska 1, Novi Sad, Serbia · Bayer A.G., Müllerstrasse 178, 13353 Berlin, Germany

  24. RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents

    May 15, 2026Zijie Dai, Shiyuan Deng, Sheng Guan +4Long-Horizon LLM AgentsAgent Memory Management

    Department of Computer Science and Engineering, The Chinese University of Hong Kong · Huawei Cloud · School of Computer Science, Beijing University of Posts and Telecommunications +2

  25. Useful Memories Become Faulty When Continuously Updated by LLMs

    May 13, 2026Dylan Zhang, Yanshan Lin, Zhengkun Wu +4AI Agent ReliabilityPersistent Memory for Language Models

    University of Illinois Urbana-Champaign · IIIS, Tsinghua University

  26. Human-Inspired Memory Architecture for LLM Agents

    May 8, 2026Doga Kerestecioglu, Alexei Robsky, Clemens Vasters +2Agent Memory ManagementLLM Agent Memory

    Microsoft

  27. Continual Knowledge Updating in LLM Systems: Learning Through Multi-Timescale Memory Dynamics

    May 6, 2026Andreas Pattichis, Constantine DovrolisContinual Learning for LLMsLLM Memory

    The Cyprus Institute, Nicosia, Cyprus · School of Computer Science, Georgia Institute of Technology, Atlanta, GA, USA.

  28. SCM: Sleep-Consolidated Memory with Algorithmic Forgetting for Large Language Models

    Apr 22, 2026Saish Sachin ShindeMemory-Augmented Language ModelsMemorization in Language Models

    Clyrai IP Studio

  29. A Wasserstein Geometric Framework for Hebbian Plasticity

    Apr 17, 2026Ulrich TanNeural Representation GeometryHebbian Learning

  30. Persistent Memory Through Triple-Loop Consolidation Under Stochastic Unit Turnover

    Mar 28, 2026Jianwei LouComputational Cognitive ModelingMemory Consolidation

    RailMind Systems, Neuss, Germany