mlsanityData to 14 Oct 2026

On Memory Construction and Retrieval for Personalized Conversational Agents

arXiv 2502.05589 ↗First posted 8 Feb 2025cs.CL cs.AIcited by 105

On the map: Retrieval-augmented generation → Conversational and speech RAG

Abstract (arXiv)

To deliver coherent and personalized experiences in long-term conversations, existing approaches typically perform retrieval augmented response generation by constructing memory banks from conversation history at either the turn-level, session-level, or through summarization techniques.In this paper, we present two key findings: (1) The granularity of memory unit matters: turn-level, session-level, and summarization-based methods each exhibit limitations in both memory retrieval accuracy and the semantic quality of the retrieved content. (2) Prompt compression methods, such as LLMLingua-2, can effectively serve as a denoising mechanism, enhancing memory retrieval accuracy across different granularities. Building on these insights, we propose SeCom, a method that constructs the memory bank at segment level by introducing a conversation segmentation model that partitions long-term conversations into topically coherent segments, while applying compression based denoising on memory units to enhance memory retrieval. Experimental results show that SeCom exhibits a significant performance advantage over baselines on long-term conversation benchmarks LOCOMO and Long-MT-Bench+. Additionally, the proposed conversation segmentation method demonstrates superior performance on dialogue segmentation datasets such as DialSeg711, TIAGE, and SuperDialSeg.

Key facts. Cited by 105 papers in the map (data through 14 Oct 2026). Placed in Conversational and speech RAG, one of 15 directions in Retrieval-augmented generation. Builds on 40 of its 65 references that are in the map. First posted on arXiv 8 Feb 2025.

Builds on

40 of 65 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Toward Conversational Agents with Context and Time Sensitive Long-term Memory29 May

Other references · 39

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  4. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  5. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  6. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  7. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  8. 2017Billion-scale similarity search with GPUscited by 2,497
  9. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 981
  10. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  11. 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 830
  12. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 828
27 more
  1. 2018CoQA: A Conversational Question Answering Challengecited by 683
  2. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 634
  3. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 556
  4. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  5. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 453
  6. 2024LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compressioncited by 348
  7. 2023LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Modelscited by 287
  8. 2021Beyond Goldfish Memory: Long-Term Open-Domain Conversationcited by 267
  9. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 184
  10. 2023Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmarkcited by 182
  11. 2024Hello Again! LLM-powered Personalized Agent for Long-term Dialoguecited by 123
  12. 2023MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversationcited by 97
  13. 2020doc2dial: A Goal-Oriented Document-Grounded Dialogue Datasetcited by 88
  14. 2023Aligning Large Language Models through Synthetic Feedbackcited by 75
  15. 2024The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Modelscited by 63
  16. 2023Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Modelscited by 62
  17. 2023Prompted LLMs as Chatbot Modules for Long Open-domain Conversationcited by 61
  18. 2023Faithful Persona-based Conversational Dataset Generation with Large Language Modelscited by 47
  19. 2020Topic-Aware Multi-turn Dialogue Modelingcited by 46
  20. 2024TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selectioncited by 39
  21. 2024LumberChunker: Long-Form Narrative Document Segmentationcited by 36
  22. 2024Boosting Conversational Question Answering with Fine-Grained Retrieval-Augmentation and Self-Checkcited by 24
  23. 2021TIAGE: A Benchmark for Topic-Shift Aware Dialog Modelingcited by 22
  24. 2021Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learningcited by 16
  25. 2023Facilitating Multi-turn Emotional Support Conversation with Positive Emotion Elicitation: A Reinforcement Learning Approachcited by 15
  26. 2023SuperDialseg: A Large-scale Dataset for Supervised Dialogue Segmentationcited by 10
  27. 2024Effective and Efficient Conversation Retrieval for Dialogue State Tracking with Implicit Text Summariescited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 26; 2026: 79.

105 papers.

Sort:

By area:

  1. 2025Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learningcited by 237
  2. 2025LightMem: Lightweight and Efficient Memory-Augmented Generationcited by 180
  3. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 126
  4. 2025In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agentscited by 106
  5. 2025How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behaviorcited by 101
  6. 2026Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agentscited by 78
  7. 2025A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applicationscited by 42
  8. 2025From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agentscited by 29
  9. 2025SGMem: Sentence Graph Memory for Long-Term Conversational Agentscited by 29
  10. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applicationscited by 25
  11. 2025Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skillscited by 22
  12. 2025LEMMA: Learning from Errors for MatheMatical Advancement in LLMscited by 21
38 more
  1. 2025MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in LLM Agent Multi-Turn Conversationscited by 21
  2. 2025Pre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized Dialoguecited by 18
  3. 2025Context Engineering 2.0: The Context of Context Engineeringcited by 18
  4. 2026HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agentscited by 18
  5. 2025Enabling Personalized Long-term Interactions in LLM-based Agents through Persistent Memory and User Profilescited by 17
  6. 2025TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulationcited by 15
  7. 2026EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agentscited by 15
  8. 2025TeleMem: Building Long-Term and Multimodal Memory for Agentic AIcited by 14
  9. 2026Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User Historycited by 14
  10. 2026Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directionscited by 14
  11. 2026ES-MemEval: Benchmarking Conversational Agents on Personalized Long-Term Emotional Supportcited by 11
  12. 2026Choosing How to Remember: Adaptive Memory Structures for LLM Agentscited by 11
  13. 2025A Survey of Scaling in Large Language Model Reasoningcited by 10
  14. 2026Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agentscited by 10
  15. 2026The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systemscited by 9
  16. 2026Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memorycited by 8
  17. 2026MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agentscited by 8
  18. 2025EpiCache: Episodic KV Cache Management for Long-Term Conversation on Resource-Constrained Environmentscited by 7
  19. 2025RGMem: Renormalization Group-inspired Memory Evolution for Language Agentscited by 7
  20. 2025Understanding and Improving Length Generalization in Hierarchical Sparse Attention Modelscited by 6
  21. 2026Chain-of-Memory: Lightweight Memory Construction with Dynamic Evolution for LLM Agentscited by 6
  22. 2025Extended Inductive Reasoning for Personalized Preference Inference from Behavioral Signalscited by 5
  23. 2025Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectivescited by 5
  24. 2026TEPA: Revoking Stale Memories for Conflict-Robust Language Agentscited by 5
  25. 2026ES-Mem: Event Segmentation-Based Memory for Long-Term Dialogue Agentscited by 4
  26. 2026Grounding Agent Memory in Contextual Intentcited by 4
  27. 2026HyMem: Hybrid Memory Architecture with Dynamic Retrieval Schedulingcited by 4
  28. 2026Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interactioncited by 4
  29. 2026ElasticMem: Latent Memory as a Learnable Resource for LLM Agentscited by 4
  30. 2026A-TMA: Decoupling State-Aware Memory Failures in Long-Term Agent Memorycited by 4
  31. 2026LeanMem: Simple and Efficient Long-Term Memory for LLM Agentscited by 4
  32. 2025The Narrative Continuity Test: A Conceptual Framework for Evaluating Identity Persistence in AI Systemscited by 3
  33. 2025Towards Proactive Personalization through Profile Customization for Individual Users in Dialoguescited by 3
  34. 2026Bi-Mem: Bidirectional Construction of Hierarchical Memory for Personalized LLMs via Inductive-Reflective Agentscited by 3
  35. 2026Rethinking Personalization in Large Language Models at the Token Levelcited by 3
  36. 2026MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexingcited by 3
  37. 2026Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agentscited by 3
  38. 2026Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainabilitycited by 3

50 most cited of 105 All 105 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory
  2. 2026OP-Bench: Benchmarking Over-Personalization for Memory-Augmented Personalized Conversational Agents
  3. 2026When Users Don't Ask: Benchmarking Context-Driven Memory Retrieval in Conversational Agents
  4. 2026AgentMemBench: A Systematic Benchmark for Evaluating Long-Term Memory Management Strategies in Conversational AI Agents
  5. 2025Convomem Benchmark: Why Your First 150 Conversations Don't Need RAG
  6. 2026M2A: Multimodal Memory Agent with Dual-Layer Hybrid Memory for Long-Term Personalized Interactions
  7. 2026TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents
  8. 2026HiGMem: A Hierarchical and LLM-Guided Memory System for Long-Term Conversational Agents