Memory-Augmented Language Models

Follow this topic Ask about this topic

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

292 papers55 papers in the last four weeks, up 90% on the four weeks before. 0.3% of all new papers.

Improving Multi-turn Dialogue Consistency with Self-Recall Thinking
May 14, 2026Renning Pang, Tian Lan, Leyuan Liu +3Memory-Augmented Language Models Long-Term Conversational Memory
University of Electronic Science and Technology of China
Emotion-Attended Stateful Memory (EASM):The Architecture for Hyper-Personalization at Scale
May 14, 2026Vineet Kotecha, Vansh GuptaMemory-Augmented Language Models Personalized Language Models
divAIne Research
A Heterogeneous Temporal Memory Governance Framework for Long-Term LLM Persona Consistency
May 14, 2026Zhao Yang, Wang Huan, Li Yingshuo +2Memory-Augmented Language Models Persona Consistency
Changchun Kelaile Technology Co., Ltd, Qinglong Road, Luyuan District, Changchun, 130000, Jilin, China. · School of Electronic Information, Zhongshan Institute, University of Electronic Science and Technology of China, No. 1 Xueyuan Road,2026 Zhongshan, 528402, Guangdong, China.
Test-Time Learning with an Evolving Library
May 14, 2026Weijia Xu, Alessandro Sordoni, Chandan Singh +4Memory-Augmented Language Models Continual Test-Time Adaptation
Microsoft Research
Stateful Reasoning via Insight Replay
May 14, 2026Bin Lei, Caiwen Ding, Jiachen Yang +2Memory-Augmented Language Models CoT Reasoning
University of Minnesota · 2Simular AI
Phasor Memory Networks: Stable Backpropagation Through Time for Scalable Explicit Memory
May 13, 2026Sungwoo Goo, Hwi-yeol Yun, Sangkeun JungMemory-Augmented Neural Networks Memory-Augmented Language Models
College of Pharmacy Chungnam National University Daejeon, South Korea · Department of Computer Science & Engineering Chungnam National University Daejeon, South Korea
Continual Fine-Tuning of Large Language Models via Program Memory
May 13, 2026Hung Le, Svetha VenkateshContinual Learning for LLMs Memory-Augmented Language Models
Deakin Applied AI Initiative, Deakin University, Australia
$δ$ -mem: Efficient Online Memory for Large Language Models
May 12, 2026Jingdi Lei, Di Zhang, Junxian Li +7Memory-Augmented Language Models Memorization in Language Models
Nanyang Technological University · Mind Lab · Fudan University +3
Automated Reformulation of Robust Optimization via Memory-Augmented Large Language Models
May 12, 2026Jinbiao Chen, Shuang Jin, Guoyun Zhang +3Memory-Augmented Language Models Large Language Model-Guided Optimization
Department of Industrial Systems Engineering and Management, National University of Singapore · Department of Data and Systems Engineering, The University of Hong Kong · Institute of Operations Research and Analytics, National University of Singapore +1
Mela: Test-Time Memory Consolidation based on Transformation Hypothesis
May 11, 2026Lungchuan ChenMemory-Augmented Neural Networks Memory-Augmented Language Models
MusubiAI
GRC: Unifying Reasoning-Driven Generation, Retrieval and Compression
May 9, 2026Zhongtao Miao, Qiyu Wu, Yoshimasa TsuruokaRetrieval-Augmented Generation Memory-Augmented Language Models
The University of Tokyo · Tsuruoka Lab. · Independent Researcher
VORT: Adaptive Power-Law Memory for NLP Transformers
May 9, 2026Nabil MlaikiMemory-Augmented Language Models Transformer
Department of Mathematics and Sciences, Prince Sultan University, Riyadh, Saudi Arabia
The Echo Amplifies the Knowledge: Somatic Marker Analogues in Language Models via Emotion Vector Re-Injection
May 9, 2026Jared GloverMemory-Augmented Language Models Causal Interventions in Language Models
CapSen Robotics
Grokers: Bottom-Up Inductive Comprehension and Write-Time Intelligence over Typed Knowledge Graphs
May 7, 2026Gregory MagarshakKG Construction Memory-Augmented Language Models
Qbix, Inc. & Intercoin, Inc. · IE University NYC · New York, NY, USA
Memory Inception: Latent-Space KV Cache Manipulation for Steering LLMs
May 7, 2026Andy Zeyi Liu, Michael Zhang, Ilana Greenberg +3Language Model Steering Memory-Augmented Language Models
Yale University · Princeton University · Jump Trading
TIDE: Every Layer Knows the Token Beneath the Context
May 7, 2026Ajay Jaiswal, Lauren Hannah, Han-Byul Kim +3Memory-Augmented Language Models Language Modeling
Apple
Contextual Memory-Enhanced Source Coding for Low-SNR Communications
May 6, 2026Ziqiong Wang, Rongpeng LiMemory-Augmented Language Models Autoregressive Language Modeling
College of Information Science and Electronic Engineering, Zhejiang University
Sparse Memory Finetuning as a Low-Forgetting Alternative to LoRA and Full Finetuning
May 4, 2026Prakhar Gupta, Garv Shah, Satyam Goyal +1Memory-Augmented Language Models LLM Fine-Tuning
University of Michigan
Evolving Token Communication with Parametric Memory Network
May 3, 2026Weixuan Chen, Qianqian YangTest-Time Adaptation Memory-Augmented Language Models
College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China
HoReN: Normalized Hopfield Retrieval for Large-Scale Sequential Model Editing
May 2, 2026Yuan Fang, Yi Xie, Xuming RanKnowledge Editing Memory-Augmented Language Models
1IXL Learning, Inc · 2Technical University of Munich · 3National University of Singapore
MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution
Apr 29, 2026Chunzheng Zhu, Jiaqi Zeng, Junyu Jiang +2Memory-Augmented Language Models Medical Image Analysis
Hunan University, Changsha, China
Learning from Execution: Self-Evolving Memory for Private-Library Code Generation
Apr 27, 2026Mofei Li, Taozhi Chen, Guowei Yang +1Memory-Augmented Language Models Knowledge Augmentation for Language Models
College of AI Tsinghua University Beijing, China · Fitten Tech Co., Ltd. Beijing, China · Emory University Atlanta, GA, USA
Graph Memory Transformer (GMT)
Apr 26, 2026Nicola Zanarini, Niccolò Ferrari, Evelina LammaMemory-Augmented Neural Networks Transformer FFNs
Bonfiglioli Engineering s.r.l. · Department of Engineering, University of Ferrara, Via Saragat 1, 44122 Ferrara, Italy · NAIS s.r.l., Via Maria Callas 4, 40131 Bologna, Italy
Evolve: A Persistent Knowledge Lifecycle for Small Language Models
Apr 25, 2026Dikran HovagimianRetrieval-Augmented Generation Memory-Augmented Language Models
Independent Researcher
Beyond N-gram: Data-Aware X-GRAM Extraction for Efficient Embedding Parameter Scaling
Apr 23, 2026Yilong Chen, Yanxi Xie, Zitian Gao +10Memory-Augmented Language Models Language Model Scaling
Institute of Information Engineering, Chinese Academy of Sciences · School of Cyber Security, University of Chinese Academy of Sciences · IQuest Research +1
Automatic Ontology Construction Using LLMs as an External Layer of Memory, Verification, and Planning for Hybrid Intelligent Systems
Apr 22, 2026Pavel Salovskii, Iuliia GorshkovaKG Construction Memory-Augmented Language Models
Partenit.io, San Francisco, CA, USA · Partenit.io San Francisco, CA, USA
SCM: Sleep-Consolidated Memory with Algorithmic Forgetting for Large Language Models
Apr 22, 2026Saish Sachin ShindeMemory-Augmented Language Models Memorization in Language Models
Clyrai IP Studio
Knowledge Capsules: Structured Nonparametric Memory Units for LLMs
Apr 22, 2026Bin Ju, Shenfeng Weng, Danying Zhou +2Memory-Augmented Language Models Knowledge Augmentation for Language Models
Zhejiang Angel Medical AI Technology Co., Ltd., Hangzhou, China · Miti AI Technology Co., Ltd., Hangzhou, China · China-Singapore Belt and Road Joint Laboratory on Translational Infection Biology for Diagnostics and Therapies, State Key Laboratory for Diagnosis and Treatment of Infectious Diseases, The First Affiliated Hospital
Absorber LLM: Harnessing Causal Synchronization for Test-Time Training
Apr 22, 2026Zhixin Zhang, Shabo Zhang, Chengcan Wu +2Memory-Augmented Language Models Long-Context Language Model Inference
1Peking University.
A Control Architecture for Training-Free Memory Use
Apr 20, 2026Yanzhen Lu, Muchen Jiang, Zhicheng Qian +1Memory-Augmented Language Models Agent Memory Management
Shanghai Qizhi Institute · Nanjing Whale Cloud · Southeast University +1

May 14, 2026J/K move · Enter open · S save

Improving Multi-turn Dialogue Consistency with Self-Recall Thinking

Renning Pang, Tian Lan, Leyuan Liu, Xiaoming Huang+2

University of Electronic Science and Technology of China

Memory-Augmented Language Models Long-Term Conversational Memory Multi-Turn Dialogue Management

Open paper AskPDF arXiv

Large language model (LLM) based multi-turn dialogue systems often struggle to track dependencies across non-adjacent turns, undermining both consistency and scalability. As conversations lengthen, essential information becomes sparse and is buried in irrelevant context, while processing the entire dialogue history incurs severe efficiency bottlenecks. Existing solutions either rely on high latency external memory or lose fine-grained details through iterative summarization. In this paper, we propose Self-Recall Thinking (SRT), a framework designed to address long-range contextual dependency and sparse informative signals in multi-turn dialogue. SRT identifies helpful historical turns and uses them to generate contextually appropriate responses, enabling the model to selectively recall and reason over context during inference. This process yields an endogenous reasoning process that integrates interpretable recall steps without external modules. SRT incorporates: (1) Dependency Construction: Generating and converting it into self-recall chains; (2)Capability Initialization: Training to enable reasoning chains with recall tokens capability; (3)Reasoning Improvement: Refining accuracy via verifiable rewards to optimize recall and reasoning for correct answers. Experiments on multiple datasets demonstrate that SRT improves F1 score by 4.7% and reduces end-to-end latency by 14.7% over prior methods, achieving a balance between reasoning latency and accuracy, and outperforming state-of-the-art baselines.