mlsanityData to 7 Oct 2026

In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents

arXiv 2503.08026 ↗First posted 11 Mar 2025cs.CL cs.AIcited by 102

On the map: LLM agents and tool use → Agent memory systems

Abstract (arXiv)

Large Language Models (LLMs) have made significant progress in open-ended dialogue, yet their inability to retain and retrieve relevant information from long-term interactions limits their effectiveness in applications requiring sustained personalization. External memory mechanisms have been proposed to address this limitation, enabling LLMs to maintain conversational continuity. However, existing approaches struggle with two key challenges. First, rigid memory granularity fails to capture the natural semantic structure of conversations, leading to fragmented and incomplete representations. Second, fixed retrieval mechanisms cannot adapt to diverse dialogue contexts and user interaction patterns. In this work, we propose Reflective Memory Management (RMM), a novel mechanism for long-term dialogue agents, integrating forward- and backward-looking reflections: (1) Prospective Reflection, which dynamically summarizes interactions across granularities-utterances, turns, and sessions-into a personalized memory bank for effective future retrieval, and (2) Retrospective Reflection, which iteratively refines the retrieval in an online reinforcement learning (RL) manner based on LLMs' cited evidence. Experiments show that RMM demonstrates consistent improvement across various metrics and benchmarks. For example, RMM shows more than 10% accuracy improvement over the baseline without memory management on the LongMemEval dataset.

Key facts. Cited by 102 papers in the map (data through 7 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 37 of its 52 references that are in the map. First posted on arXiv 11 Mar 2025.

Builds on

37 of 52 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Towards Lifelong Dialogue Agents via Timeline-based Memory Management16 Jun
  2. 2024Hello Again! LLM-powered Personalized Agent for Long-term Dialogue9 Jun
  3. 2024Evaluating Very Long-Term Conversational Memory of LLM Agents27 Feb

Other references · 34

  1. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  2. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  3. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  4. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  5. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  6. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 705
  7. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 656
  8. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 539
  9. 2023Ring Attention with Blockwise Transformers for Near-Infinite Contextcited by 448
  10. 2024Agent Workflow Memorycited by 342
  11. 2021Beyond Goldfish Memory: Long-Term Open-Domain Conversationcited by 266
  12. 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Securitycited by 257
22 more
  1. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 203
  2. 2014A* Samplingcited by 150
  3. 2024Simulating Classroom Education with LLM-Empowered Agentscited by 125
  4. 2024Jasper and Stella: distillation of SOTA embedding modelscited by 109
  5. 2025On Memory Construction and Retrieval for Personalized Conversational Agentscited by 101
  6. 2024Personalization of Large Language Models: A Surveycited by 100
  7. 2023MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversationcited by 94
  8. 2023When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunitiescited by 89
  9. 2022Keep Me Updated! Memory Management in Long-term Conversationscited by 62
  10. 2023Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Modelscited by 62
  11. 2023Prompted LLMs as Chatbot Modules for Long Open-domain Conversationcited by 61
  12. 2024SCBench: A KV Cache-Centric Analysis of Long-Context Methodscited by 59
  13. 2025ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inferencecited by 57
  14. 2024Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approachcited by 40
  15. 2023Length Extrapolation of Transformers: A Survey from the Perspective of Positional Encodingcited by 32
  16. 2024DAPE: Data-Adaptive Positional Encoding for Length Extrapolationcited by 30
  17. 2024ALR2: A Retrieve-then-Reason Framework for Long-context Question Answeringcited by 25
  18. 2024Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)cited by 20
  19. 2024On the Benchmarking of LLMs for Open-Domain Dialogue Evaluationcited by 10
  20. 2024Attribute or Abstain: Large Language Models as Long Document Assistantscited by 10
  21. 2021A Cooperative Memory Network for Personalized Task-oriented Dialogue Systems with Incomplete User Profilescited by 8
  22. 2024SPAR: Personalized Content-Based Recommendation via Long Engagement Attentioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 16; 2026: 86.

102 papers.

Sort:

By area:

  1. 2025ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memorycited by 253
  2. 2025SGMem: Sentence Graph Memory for Long-Term Conversational Agentscited by 29
  3. 2025A Survey on Autonomy-Induced Security Risks in Large Model-Based Agentscited by 28
  4. 2025From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agentscited by 27
  5. 2026TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agentscited by 26
  6. 2025FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoningcited by 25
  7. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applicationscited by 22
  8. 2025Multi-Agent Debate for LLM Judges with Adaptive Stability Detectioncited by 20
  9. 2026REMem: Reasoning with Episodic Memory in Language Agentcited by 20
  10. 2025A Survey on Agentic Multimodal Large Language Modelscited by 19
  11. 2026HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agentscited by 16
  12. 2026Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregationcited by 15
38 more
  1. 2026MemoryCD: Benchmarking Long-Context User Memory of LLM Agents for Lifelong Cross-Domain Personalizationcited by 15
  2. 2026Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agentscited by 14
  3. 2026MemBuilder: Reinforcing LLMs for Long-Term Memory Construction via Attributed Dense Rewardscited by 13
  4. 2026StackPlanner: A Centralized Hierarchical Multi-Agent System with Task-Experience Memory Managementcited by 13
  5. 2025Learning from Diverse Reasoning Paths with Routing and Collaborationcited by 12
  6. 2026GroupMemBench: Benchmarking LLM Agent Memory in Multi-Party Conversationscited by 12
  7. 2025Agentic Learner with Grow-and-Refine Multimodal Semantic Memorycited by 11
  8. 2026Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memorycited by 11
  9. 2026EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agentscited by 11
  10. 2025AssoMem: Scalable Memory QA with Multi-Signal Associative Retrievalcited by 10
  11. 2026GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)cited by 10
  12. 2026Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agentscited by 9
  13. 2026MemSyco-Bench: Benchmarking Sycophancy in Agent Memorycited by 9
  14. 2026AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-Playingcited by 8
  15. 2026All-Mem: Agentic Lifelong Memory via Dynamic Topology Evolutioncited by 8
  16. 2025EpiCache: Episodic KV Cache Management for Long-Term Conversation on Resource-Constrained Environmentscited by 7
  17. 2025RGMem: Renormalization Group-inspired Memory Evolution for Language Agentscited by 7
  18. 2025Who's Your Judge? On the Detectability of LLM-Generated Judgmentscited by 6
  19. 2025Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstructioncited by 6
  20. 2026Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agentscited by 6
  21. 2026Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agentscited by 6
  22. 2026PM-Bench: Evaluating Prospective Memory in LLM Agentscited by 6
  23. 2026Infini Memory: Maintainable Topic Documents for Long-Term LLM Agent Memorycited by 5
  24. 2026RaMem: Contextual Reinstatement for Long-term Agentic Memorycited by 5
  25. 2026HyMem: Hybrid Memory Architecture with Dynamic Retrieval Schedulingcited by 4
  26. 2026FragFuse: Bypassing Access Control of Large Language Model Agents via Memory-Based Query Fragmentation and Fusioncited by 4
  27. 2026LeanMem: Simple and Efficient Long-Term Memory for LLM Agentscited by 4
  28. 2026From Atom to Community: Structured and Evolving Agent Memory for User Behavior Modelingcited by 3
  29. 2026M2: Dual-Memory Augmentation for Long-Horizon Web Agents via Trajectory Summarization and Insight Retrievalcited by 3
  30. 2026Oblivion: Self-Adaptive Agentic Memory Control through Decay-Driven Activationcited by 3
  31. 2026Hierarchical Memory Orchestration for Personalized Persistent Agentscited by 3
  32. 2026MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexingcited by 3
  33. 2026Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-horizon Agentscited by 3
  34. 2026Memory Retrieval for Changing Preferencescited by 3
  35. 2026SKILL.nb: Selective Formalization and Gated Execution for Durable Agent Workflowscited by 3
  36. 2026DynamicMem: A Long-Horizon Memory Benchmark in Real-World Settingscited by 3
  37. 2026C2KV: Compressed and Composable KV Cache Reuse for Efficient LLM Inferencecited by 3
  38. 2025Patient-Zero: Scaling Synthetic Patient Agents to Real-World Distributions without Real Patient Datacited by 2

50 most cited of 102 All 102 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026MGRetrieval: Memory-Guided Reflective Retrieval for Long-Term Dialogue Agents
  2. 2026AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents
  3. 2026Multi-Layered Memory Architectures for LLM Agents: An Experimental Evaluation of Long-Term Context Retention
  4. 2024"My agent understands me better": Integrating Dynamic Human-like Memory Recall and Consolidation in LLM-Based Agents
  5. 2025A Simple Yet Strong Baseline for Long-Term Conversational Memory of LLM Agents
  6. 2026MemToolAgent: Leveraging Memory for Tool Using Agents Based on Environment and User Feedback
  7. 2025Memoria: A Scalable Agentic Memory Framework for Personalized Conversational AI
  8. 2025Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics