Overview

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event timelines, graphs, or speaker-specific states; many also add rules for updating facts and filtering uncertain or outdated information.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

CardsList

78 papers11 papers in the last four weeks, down 39% on the four weeks before. 0.1% of all new papers.

  1. How Much Conversation History Does an AI Agent Need?

    Nov 6, 2026Danny Kim, Fernando KochLLM Context ManagementConversational Memory

  2. The Right Source Is Not Enough: Understanding History Interference in Speech-LLM Memory

    Nov 3, 2026HongJin Song, Weiqiao Shan, Runwu Shi +11Conversational MemorySpeech Language Models

  3. One Assistant, Many Memories: Benchmarking Real-World Group Assistance When Recall Is Not Enough

    Nov 3, 2026Zhanghao Hu, Linhai Zhang, Qian Zhao +8Memory Agent BenchmarksConversational Memory

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

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

  5. Chain on Demand: Deferred Evidence Organization for Long-Term Conversational Memory

    Nov 2, 2026Di Lu, Zechen Li, Hao XueLong-Term Conversational MemoryConversational Memory

  6. 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 EvaluationLLM Agents

  7. Self-Keyed In-Parameter Memorization for External Memory-Free Dialogue Recall in Frozen Language Models

    Oct 27, 2026XinYu Piao, Myunghoon Ryu, Joongheon Kim +1Conversational MemoryMemorization in Language Models

  8. TrawMem: Reframing Agent Memory as Task-Oriented Role-Adaptive Workspaces

    Oct 27, 2026Mingyu Zhang, Zixu Li, Zhiheng Fu +3LLM Agent MemoryMemory Management for LLM Agents

  9. From Voiceprints to User Entities: Online Speaker-Memory Construction for Multi-User Spoken Agents

    Oct 27, 2026Yucong Zhang, Cancan Li, Bo Xiao +2Conversational MemoryMemory-Augmented Language Model Agents

  10. DiaLong: Benchmarking Reminiscence in Long-Context Dialogues

    Oct 18, 2026Owen Bianchi, Samer Aslan, Ryunosuke SaitoConversational MemoryLong-Context Language Model Evaluation

  11. EGCForest: Structured Agent Memory Organization for Enterprise Group Chats

    Oct 14, 2026Lingxi Cui, Jinhao Ruan, Wenqing Wei +4Conversational MemoryEvidence Retrieval

  12. New Model, Old Habits: Behavior Transfer under Model Swapping in Multi-Session LLM Agents

    Oct 14, 2026Youngbin Choi, Sehyun Hwang, Suhyeon Jun +4LLM AgentsMulti-LLM Collaboration

  13. Temporal Evidence Forests for Long-Horizon Multi-Party Conversational Memory

    Oct 9, 2026Junyou Guo, Chongyang Tao, Yan He +2LLM Agent MemoryConversational Memory

  14. Gated Memory: Admission-Controlled Memory Formation for Conversational AI

    Oct 8, 2026Preeti Saraswat, Divya Neelagiri, Ajay ManojConversational MemoryLong-Term Conversational Memory

  15. PERSIST: Who-What-When Memory Across Sessions for Full-Duplex Spoken Dialogue

    Oct 6, 2026Achira Lin, Siyuan Hou, Wenyi Yu +7Conversational MemoryPersistent Memory for Language Models

  16. Grounding Memory Summarization in Utility Intent

    Sep 27, 2026Zhenyu Lei, Mingjia Shi, Xingbo Fu +3Conversational MemoryLLM Memory

  17. Beyond Memory Construction: Rethinking Memory Access for LLM-based Conversational Agents

    Sep 27, 2026Donghua Cai, Yongheng Deng, Yifei Wang +2LLM Agent MemoryConversational Memory

  18. Mutable Transcripts: Mitigating Context Pollution through Editable Conversation State

    Sep 25, 2026Dan Barry, Andrew HinesLLM Context ManagementConversational Memory

  19. SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue

    Sep 22, 2026Haobo Zheng, Tan Tang, Yan Chen +2Conversational MemoryLLM Memory