Memory-Augmented Language Models

Overview

Memory-augmented language models study how systems can store information from documents, conversations, or earlier tasks and use it in later responses. Approaches include retrieval-augmented generation and structured episodic stores, reusable key-value caches and latent or parametric adapters, and recurrent or fast-weight memories; many add selective writing, compression, routing, or forgetting. Work tests these methods on long-context question answering and recall, reasoning, and continual personalization, using benchmarks such as LoCoMo, LongMemEval, and RULER. Memory can improve access to distant or newly learned information, but systems still struggle with noisy or changing memories, interference with existing capabilities, and evaluations that distinguish successful storage from useful and reliable retrieval.

Latest papers

CardsList

314 papers23 papers in the last four weeks, down 62% on the four weeks before. 0.2% of all new papers.

  1. Kernel Ridge Attention: Nonlinear Memory with Selective Forgetting

    Nov 18, 2026Haowei Chen, Yichen Wang, Congfu XuAttention MechanismsMemory-Augmented Language Models

  2. Toaster: Nonlinear Memory from Cascaded Linear Memories and Target Propagation

    Nov 18, 2026Zeman Li, Ali Behrouz, Yuan Deng +4Memory-Augmented Language ModelsDelta-Rule Linear Attention

  3. Natural Language Programming: Rethinking Language, Memory, and Cognition in the Era of Generative AI

    Nov 17, 2026Giovanni Adorni, Daniele GrossoLLM PromptingWorking Memory in Language Models

  4. MemEmo: Evaluating Emotion in Memory Systems

    Nov 16, 2026Peng Liu, Zhen Tao, Jihao Zhao +5Memory-Augmented Language ModelsMemory Agent Benchmarks

  5. MIGRO: A Decoupled and Portable Long-Term Memory System for Language Models

    Nov 11, 2026Mingxi Zou, Yinghui Xu, Jiaxiang Chen +10Persistent Memory for Language ModelsLong-Term Conversational Memory

  6. Self-Indexing Latent Memories for Access-Aware Continual Instruction Tuning of LLMs

    Nov 8, 2026Dhruv Dixit, Paritosh Pandey, Snehalkumar 'Neil' S. GaikwadContinual Learning for LLMsInstruction Tuning

  7. EASE-KV: Diagnosing the Gap Between Memory Availability and Effective Use

    Nov 8, 2026Di Lu, Zechen Li, Xuanyu Yue +3Memory-Augmented Language ModelsPersistent Memory for Language Models

  8. ASCENT: Scale-Complementary External State for Frozen Long-Context Language Models

    Nov 6, 2026Xingjian ZhangMemory-Augmented Language ModelsLong-Context Language Modeling

  9. Retrofitting Unbounded Context onto Stock Language Models

    Nov 6, 2026Mark OskinLong-Context Language Model InferenceLanguage Modeling

  10. Route to Remember: Adaptive Memory Selection for LLM Agents

    Nov 3, 2026Zeyu Fang, Jun Yin, Yongsheng Mei +8Memory Management for LLM AgentsMemory-Augmented Language Models

  11. Going Deeper With Memories

    Nov 3, 2026Afshin KhadangiLanguage ModelingByte-Level Language Model

  12. Anchor: Augmented Cross-Layer Recurrent State for Long-Context Retrieval in Test-Time Training

    Nov 3, 2026Vimal William, Yuanzhe Li, Danella Zhao +1Memory-Augmented Language ModelsLong-Context Retrieval

  13. Scalaris: A Scalable Enterprise Memory Architecture for Conversational AI Assistants

    Nov 2, 2026Devarsh Gandhi, Sarthak Pawar, Hemprasad Badgujar +3Conversational MemoryMemory Management for LLM Agents

  14. MemShift: Separating Detection from Repair in LLM-Derived Personal Memory

    Nov 2, 2026Zichuan Xu, Haochen Zhang, Yuyang Dong +2Memory-Augmented Language ModelsLanguage Model Error Detection

  15. ParaTTT: Parallelizing Test-Time Training Layers with Deep Memories

    Oct 28, 2026Noel Loo, Neehal Tumma, T. Konstantin Rusch +3Test-Time TrainingRecurrent Language Models

  16. ETAMem: Decoupling and Aligning Heterogeneous Memory for Long-Term Conversational Agents

    Oct 27, 2026Xinying Qian, Ying Zhang, Yu Zhao +3Memory Management for LLM AgentsLong-Term Conversational Memory

  17. CRIM: Composable and Reusable Item Memory for Efficient Personalized Retrieval

    Oct 26, 2026Haolin Li, Haipeng Zhang, Mang Li +5Information RetrievalMemory-Augmented Language Models

  18. Let the Gate Decide: Per-Lookup Precision for Quantized Conditional Memory in LLMs

    Oct 26, 2026Tianqi Chen, Xunchao Li, Linchuan Xie +4Memory-Augmented Language ModelsLLM Quantization

  19. Memory-Aware Reward Modeling: Learning Human Preferences for LLM Memory Use

    Oct 22, 2026Yijiang River Dong, Zexue He, Cheng Yu +9Memory-Augmented Language ModelsReward Modeling