Conversational Memory

Follow this topic Ask about this topic

Conversational memory studies how AI assistants can preserve and reuse information from earlier interactions so they can answer follow-up questions, adapt to changing preferences, and maintain continuity. Systems range from searching raw chat logs with lexical or vector retrieval and reranking to storing summaries, event timelines, graphs, or speaker-specific states; many also add rules for updating facts and filtering uncertain or outdated information. Benchmarks such as LoCoMo and LongMemEval test long-range recall, while newer group and lifecycle evaluations examine speaker attribution, changing facts, and whether memories are used naturally in conversation. A central tension is whether elaborate structured memory improves reliability enough to justify its cost, since simple retrieval can be competitive and better recall does not always lead to better answers or user experience.

Latest papers

71 papers13 papers in the last four weeks, down 13% on the four weeks before. 0.1% of all new papers.

Finding Is Not Returning, Returning Is Not Reconstructing: A Multi-Dimensional Evaluation of Agent Social Re-entry
Oct 29, 2026Sheng Wan, Cong Ma, Sichen Dong +4LLM Agent Evaluation LLM Agents
The Hong Kong University of Science and Technology, Hong Kong, China · Southern University of Science and Technology, Shenzhen, China · City University of Hong Kong, Hong Kong, China +4
Self-Keyed In-Parameter Memorization for External Memory-Free Dialogue Recall in Frozen Language Models
Oct 27, 2026XinYu Piao, Myunghoon Ryu, Joongheon Kim +1Conversational Memory Memorization in Language Models
Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea
TrawMem: Reframing Agent Memory as Task-Oriented Role-Adaptive Workspaces
Oct 27, 2026Mingyu Zhang, Zixu Li, Zhiheng Fu +3LLM Agent Memory Memory Management for LLM Agents
Shandong University · National University of Singapore
From Voiceprints to User Entities: Online Speaker-Memory Construction for Multi-User Spoken Agents
Oct 27, 2026Yucong Zhang, Cancan Li, Bo Xiao +2Conversational Memory Memory-Augmented Language Model Agents
School of Computer Science, Wuhan University · School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen · Meituan
The Geometry of Agent Memory: Forecasting Retrieval-Bound Memory Failures, and Characterizing Its Limits
Oct 19, 2026Iliya Zhechev, Radoslav Ralev, Chris Coleman +4LLM Memory Conversational Memory
Redis
DiaLong: Benchmarking Reminiscence in Long-Context Dialogues
Oct 18, 2026Owen Bianchi, Samer Aslan, Ryunosuke SaitoConversational Memory Long-Context Language Model Evaluation
Center for Language and Speech Processing, Johns Hopkins University
EGCForest: Structured Agent Memory Organization for Enterprise Group Chats
Oct 14, 2026Lingxi Cui, Jinhao Ruan, Wenqing Wei +4Conversational Memory Evidence Retrieval
The State Key Laboratory of Blockchain and Data Security, Zhejiang University · Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security · Xiaohongshu
New Model, Old Habits: Behavior Transfer under Model Swapping in Multi-Session LLM Agents
Oct 14, 2026Youngbin Choi, Sehyun Hwang, Suhyeon Jun +4LLM Agents Multi-LLM Collaboration
Graduate School of Artificial Intelligence, POSTECH · Meta · Department of Computer Science and Engineering, POSTECH
Do Personalized LLMs Need the Whole Conversation? Matching the Full History with Only 5% of Its Text via Relevance-Filtered Context
Oct 10, 2026Erika Hayashi, Andrew ShinLLM Context Management Conversational Memory
Keio University
Temporal Evidence Forests for Long-Horizon Multi-Party Conversational Memory
Oct 9, 2026Junyou Guo, Chongyang Tao, Yan He +2LLM Agent Memory Conversational Memory
School of Computer Science and Engineering, Beihang University, Beijing, China · Alibaba Group
Gated Memory: Admission-Controlled Memory Formation for Conversational AI
Oct 8, 2026Preeti Saraswat, Divya Neelagiri, Ajay ManojConversational Memory Long-Term Conversational Memory
Samsung Research America, Mountain View, CA
Memory Depth and Reconstructed Context Width: A Controlled Evaluation of Hierarchical Retrieval
Oct 6, 2026Michael AndreevConversational Memory LLM Evaluation
Independent Researcher
PERSIST: Who-What-When Memory Across Sessions for Full-Duplex Spoken Dialogue
Oct 6, 2026Achira Lin, Siyuan Hou, Wenyi Yu +7Conversational Memory Persistent Memory for Language Models
Tsinghua University · Huawei Technologies Ltd.
AgentMemGate: Addressing Speculation Contamination in Conversational Assistant Memory
Oct 6, 2026Chirag Sharma, Benjamin Fowlersmith, Karime MaamariConversational Memory Long-Term Conversational Memory
Distyl AI
Have I Scene This Before? Spatially Grounded Conversational Memory for Complex Queries in Egocentric Assistants
Oct 4, 2026Jiazhou Liang, Liam Gallagher, Kiko Chen +4Conversational Memory Egocentric Video Understanding
University of Toronto
AMU:Admission and Memory Update for Personalized Conversations---Structured Memory with SLM Guided Control
Sep 29, 2026Tao Hwang, Yishi DiaoConversational Memory Persistent Memory for Language Models
Independent Researcher · Nanchang University
When Does Selection Replace Extraction? A Pre-Registered Test of Agent Memory with a Typed Decision Model
Sep 28, 2026Rishabh Sharma, Rishika LallConversational Memory LLM Reranking
Independent Researcher
Grounding Memory Summarization in Utility Intent
Sep 27, 2026Zhenyu Lei, Mingjia Shi, Xingbo Fu +3Conversational Memory LLM Memory
University of Virginia · Northeastern University
Beyond Memory Construction: Rethinking Memory Access for LLM-based Conversational Agents
Sep 27, 2026Donghua Cai, Yongheng Deng, Yifei Wang +2LLM Agent Memory Conversational Memory
Tsinghua University · Beijing Institute of Technology · Nanjing University
Beyond Dyadic Memory: Interaction-Aware Multimodal Memory with Adaptive Agentic Retrieval for Multi-Party Spoken Conversations
Sep 26, 2026Wenxu Jia, Xize Cheng, Zihan Zhang +5Conversational Memory Multimodal Memory
Zhejiang University · Meituan
Mutable Transcripts: Mitigating Context Pollution through Editable Conversation State
Sep 25, 2026Dan Barry, Andrew HinesLLM Context Management Conversational Memory
School of Computer Science University College Dublin Dublin, Ireland
TWIST: A Proposed Benchmark for Intervention Quality in Conversational Memory, with a Human-Validated Draft-Alignment
Sep 23, 2026Subrat PandaConversational Memory Memory Agent Benchmarks
MindTwin
SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue
Sep 22, 2026Haobo Zheng, Tan Tang, Yan Chen +2Conversational Memory LLM Memory
State Key Lab of CAD&CG, Zhejiang University
Propose, Verify, Commit: Evidence-Grounded Memory for Long-Horizon Multi-Actor Conversations
Sep 20, 2026Zihao Lu, Zhihang Yuan, Litu Ou +1Conversational Memory Persistent Memory for Language Models
Alibaba Cloud Computing, Hangzhou, China
JustMem: Just-Enough Memory Access for Long-Term Conversations
Sep 17, 2026Guanhua Chen, Yanting Wang, Wenjing Zhi +1Conversational Memory Conversational QA
Beihang University
LSREP: A Longitudinal State-Replay Protocol for Evaluating Conversational Memory, with ICE v2 as an Audited Local-First Architecture
Sep 15, 2026Deepesh SonarConversational Memory Memory Agent Benchmarks
Thakur College of Engineering and Technology, Computer Engineering, Mumbai, India
CueMem: Cue-Guided Context Reconstruction for Long-Term Conversational Memory
Sep 11, 2026Changjian Wang, Rongzhen Li, Weili Guan +3Conversational Memory Long-Term Conversational Memory
Mashang Consumer Finance Co., Ltd. · Harbin Institute of Technology, Shenzhen
Fortunate Recall: Ontology-Driven Memory Lifecycle Management for Persistent Coherence in LLMs
Sep 9, 2026Ansuman Mullick, Eray TüzünConversational Memory Temporal Reasoning in Language Models
Bilkent University
PRAGMA: Evaluating Personalized Guidance with Memory Alignment in Lifelong Conversations
Sep 9, 2026Hyojeong Yu, Hyukhun Koh, Minsung Kim +2Conversational Memory Persistent Memory for Language Models
Dept. of ECE, Seoul National University · IPAI, Seoul National University
Personalizing LLM Agent Memory Using Biometrics
Sep 8, 2026Yanhong Qian, Qingguo Meng, Shihao Ding +4Conversational Memory LLM Agent Memory
Anhui Provincial Key Laboratory of Secure Artificial Intelligence, School of Artificial Intelligence, Anhui University, Hefei 230093, China · National Institute of Informatics, Tokyo 101-8430, Japan

Oct 29, 2026J/K move · Enter open · S save

Finding Is Not Returning, Returning Is Not Reconstructing: A Multi-Dimensional Evaluation of Agent Social Re-entry

Sheng Wan, Cong Ma, Sichen Dong, Qian'Ang Mao+3

The Hong Kong University of Science and Technology, Hong Kong, China · Southern University of Science and Technology, Shenzhen, China · City University of Hong Kong, Hong Kong, China+4

LLM Agent Evaluation LLM Agents Conversational Memory Long-Term Conversational Memory

Open paper AskPDF arXiv

As Large Language Model (LLM) agents increasingly participate in persistent social environments, understanding their long-term social interaction capabilities becomes increasingly important. While existing research has advanced long-term memory and conversational context retrieval, less attention has been paid to whether agents can autonomously re-engage with previously inactive conversations. In particular, remembering a past interaction does not necessarily mean that an agent can identify when to revisit it, decide to return, or reconstruct the context needed for a coherent continuation. To investigate this gap, we introduce agent social re-entry as a multi- dimensional evaluation problem, distinguishing three complementary capabilities: Finding, Returning, and Reconstructing. We develop a shared-snapshot evaluation framework that measures these dimensions independently, allowing us to examine how conversational resurfacing and persistent memory relate to different aspects of social re-entry. Evaluations across six LLM configurations show that resurfacing substantially improves target conversation identification, while persistent memory is associated with higher rates of autonomous target-directed replying. However, neither improvement is accompanied by consistent gains in contextual reconstruction. These results highlight the distinction between accessing previous conversations, choosing to re-engage, and maintaining conversational continuity. Our framework provides a way to evaluate these capabilities separately rather than relying on memory retrieval or conversational response quality alone.