Long-Term Conversational Memory

Follow this topic Ask about this topic

Long-term conversational memory studies how AI assistants can carry forward useful facts, preferences, events, and user states across extended interactions. Systems variously preserve raw dialogue or compress it into facts, summaries, timelines, or graphs, then use lexical and semantic search, structured traversal, and query-guided reasoning to retrieve evidence. Benchmarks such as LoCoMo and LongMemEval test factual recall, temporal updates, and multi-hop reasoning, while newer evaluations probe realistic interaction, personalization, and memory use. A central tension is balancing accurate, traceable evidence and reliable updates with bounded storage, retrieval cost, privacy, and resistance to stale or misleading memories.

Latest papers

269 papers53 papers in the last four weeks, up 39% on the four weeks before. 0.3% of all new papers.

WhenLoss: Diagnosing Write and Retrieval Bottlenecks in Long-Context Memory Systems
May 23, 2026Jiangnan Yu, Kisson Songqi Lin, Jilong WuLong-Context Retrieval Memory-Augmented Language Models
MGRetrieval: Memory-Guided Reflective Retrieval for Long-Term Dialogue Agents
May 22, 2026Tan Wang, Yunwei DongPersistent Memory for Language Models Agentic Retrieval
Northwestern Polytechnical University Xi’an, Shaanxi, China
OnePred: Next-Query Prediction via Recursive Intent Memory in Multi-Turn Conversations
May 22, 2026Jiangwang Chen, Bowen Zhang, Zixin Song +4Long-Term Conversational Memory Efficient Language Model Inference
1Tsinghua University · 2Qwen Applications Business Group of Alibaba
DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Agent Memory
May 21, 2026Jianing Yin, Tan Tang, Yingcai WuLLM Agent Memory Persistent Memory for Language Models
State Key Lab of CAD&CG, Zhejiang University
Psy-Chronicle: Synthesizing Campus Counseling Grounded in a Student's Semester Timeline
May 21, 2026Chaogui GouMental Health Counseling Emotional Support Conversation
University of Science and Technology Beijing
Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory
May 19, 2026Jingwei Sun, Jianing Zhu, Jiangchao Yao +2Memorization in Language Models LLM Agent Memory
TMLR Group, Hong Kong Baptist University · The University of Texas at Austin · Shanghai Jiao Tong University +1
Synthesis and Evaluation of Long-term History-aware Medical Dialogue
May 19, 2026Hebin Hu, Renke Dai, Ah-Hwee Tan +1Healthcare AI Agent Benchmarks
South-Central Minzu University Wuhan, China · Singapore Management University Singapore, Singapore
Causal Intervention-Based Memory Selection for Long-Horizon LLM Agents
May 17, 2026Saksham Sahai SrivastavaConversational Memory Long-Term Conversational Memory
School of Computing, University of Georgia, Athens, Georgia, USA.
NeuSymMS: A Hybrid Neuro-Symbolic Memory System for Persistent, Self-Curating LLM Agents
May 17, 2026Mujahid Sultan, Sri Thuraisamy, Daya RajaratnamLLM Agent Memory Neuro-Symbolic Reasoning
†MLSoft Inc., Toronto, Ontario, Canada · ∗iVedha Corporation, Toronto, Ontario, Canada
MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing
May 16, 2026Han Chen, Zining Zhang, Wenqi Pei +6LLM Agent Memory Hierarchical Memory
National University of Singapore · Singapore, Singapore · Zero Gravity Labs +1
DimMem: Dimensional Structuring for Efficient Long-Term Agent Memory
May 15, 2026Wentao Qiu, Haotian Hu, Fanyi Wang +2LLM Agent Memory Persistent Memory for Language Models
1StepOS · 2Xiamen University · 3ShanghaiTech University
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.
GroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversations
May 14, 2026Jingbo Yang, Kwei-Herng Lai, Xiaowen Wang +3Conversational Memory LLM Agent Evaluation
UC Santa Barbara · Microsoft
Thinking Ahead: Prospection-Guided Retrieval of Memory with Language Models
May 13, 2026Harshita Chopra, Krishna Kant Chintalapudi, Suman Nath +2Retrieval-Augmented Generation Long-Term Conversational Memory
University of Washington, Seattle, USA · 2Microsoft Research, Redmond, USA
EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents
May 13, 2026Jiaqi Liu, Xinyu Ye, Peng Xia +4LLM Agent Memory LLM Memory
UNC-Chapel Hill · UC Berkeley · UCSC
CogniFold: Always-On Proactive Memory via Cognitive Folding
May 13, 2026Suli Wang, Yiqun Duan, Yu Deng +5Cognitive Architectures for AI Agents Continual Learning
1OpenNorve · University of Cambridge · 3NVIDIA +1
PRISM: Pareto-Efficient Retrieval over Intent-Aware Structured Memory for Long-Horizon Agents
May 12, 2026Jingyi Peng, Zhongwei Wan, Weiting Liu +1Graph-Based Retrieval Information Retrieval
Singapore Management University · The Ohio State University · Fudan University
Goal-Oriented Reasoning for RAG-based Memory in Conversational Agentic LLM Systems
May 12, 2026Jiazhou Liang, Armin Toroghi, Yifan Simon Liu +3Multi-Hop QA Agentic RAG
University of Toronto · Vector Institute for Artificial Intelligence
Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory
May 11, 2026Mingxi Zou, Zhihan Guo, Langzhang Liang +6Rate-Distortion Theory Long-Term Conversational Memory
Fudan University · The Chinese University of Hong Kong · Meta AI +3
Human-Inspired Memory Architecture for LLM Agents
May 8, 2026Doga Kerestecioglu, Alexei Robsky, Clemens Vasters +2Agent Memory Management LLM Agent Memory
Microsoft
When Stored Evidence Stops Being Usable: Scale-Conditioned Evaluation of Agent Memory
May 8, 2026Jiaqi Shao, Yiyi Lu, Yunzhen Zhang +1Agent Memory AI Agent Evaluation
Hong Kong University of Science and Technology, Hong Kong · Duke Kunshan University, China
Storage Is Not Memory: A Retrieval-Centered Architecture for Agent Recall
May 6, 2026Joshua Adler, Guy ZehaviAgent Memory LLM Agent Memory
Sauron Labs
MEMAUDIT: An Exact Package-Oracle Evaluation Protocol for Budgeted Long-Term LLM Memory Writing
May 4, 2026Nishant Bhargava, Rodrigo Sobral BarrentoPersistent Memory for Language Models LLM Agent Evaluation
Purdue University
GRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memory
May 3, 2026Yushi Sun, Bowen Cao, Dong Fang +2LLM Agent Memory Persistent Memory for Language Models
LIGHTSPEED, Shenzhen, China · The Chinese University of Hong Kong, Hong Kong, China
MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents
May 2, 2026Hung Pham Van, Nguyen Manh Hieu, Khang Pham Tran Tuan +4Conversational Memory Graph Retrieval-Augmented Generation
1Independent Researcher · 2Hanoi University of Science and Technology · 3VNU University of Engineering and Technology +1
Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory
May 1, 2026Derong Xu, Shuochen Liu, Pengfei Luo +8Memorization in Language Models Memorization in Generative Models
University of Science and Technology of China & State Key Laboratory of Cognitive Intelligence · City University of Hong Kong · Dalian University of Technology +1
MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents
May 1, 2026Tianyu Hu, Weikai Lin, Weizhi Zhang +2Persistent Memory for Language Models Long-Term Conversational Memory
University of Central Florida · University of Rochester · University of Illinois at Chicago +1
EviMem: Evidence-Gap-Driven Iterative Retrieval for Long-Term Conversational Memory
Apr 30, 2026Yuyang Li, Yime He, Zeyu Zhang +1Temporal IR Evidence Retrieval
The Australian National University · UNSW Sydney

May 23, 2026J/K move · Enter open · S save

WhenLoss: Diagnosing Write and Retrieval Bottlenecks in Long-Context Memory Systems

Jiangnan Yu, Kisson Songqi Lin, Jilong Wu

Long-Context Retrieval Memory-Augmented Language Models Memory Compression Long-Term Conversational Memory

Open paper AskPDF arXiv

Long-context memory systems often fail under fixed budgets, but end-to-end evaluation does not reveal whether evidence was discarded during compression or preserved but never retrieved. We introduce a four-condition diagnostic protocol that evaluates a fixed reader under truncated full context (TFC), oracle evidence (OE), complete stored memory (CSM), and retrieved memory (RM). Under this fixed-budget LongMemEval setup, write-side gaps exceed retrieval-side gaps for most tested baselines, with four of six baselines robustly write-dominant under our default diagnosis margin. Motivated by this diagnosis, we propose Expected Predictive Compression (EPC), which moves the key decision--what information to retain--to write time by using an LLM to anticipate likely future questions and preserve the minimal supporting evidence under the token budget, while leaving retrieval unchanged at question time. Across all 500 LongMemEval questions with three readers (GPT-5.2, Claude Sonnet 4, Gemini 2.5 Pro), EPC achieves the highest CSM scores among all systems (0.49 vs. 0.44 for Summary (LLM), the strongest baseline), reducing Delta_write to 0.04 while leaving Delta_retr comparable to other LLM-based systems. These results suggest that, on this benchmark and evaluation setup, improving what the write stage preserves is a key avenue for performance gains in the tested systems.