mlsanityData to 7 Oct 2026

Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models

arXiv 2308.15022 ↗First posted 29 Aug 2023cs.CL cs.AIcited by 62

Not on the map. Why?

Cited by 28 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recently, large language models (LLMs), such as GPT-4, stand out remarkable conversational abilities, enabling them to engage in dynamic and contextually relevant dialogues across a wide range of topics. However, given a long conversation, these chatbots fail to recall past information and tend to generate inconsistent responses. To address this, we propose to recursively generate summaries/ memory using large language models (LLMs) to enhance long-term memory ability. Specifically, our method first stimulates LLMs to memorize small dialogue contexts and then recursively produce new memory using previous memory and following contexts. Finally, the chatbot can easily generate a highly consistent response with the help of the latest memory. We evaluate our method on both open and closed LLMs, and the experiments on the widely-used public dataset show that our method can generate more consistent responses in a long-context conversation. Also, we show that our strategy could nicely complement both long-context (e.g., 8K and 16K) and retrieval-enhanced LLMs, bringing further long-term dialogue performance. Notably, our method is a potential solution to enable the LLM to model the extremely long context. The code and scripts are released.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). Builds on 45 of its 63 references that are in the map. First posted on arXiv 29 Aug 2023.

Builds on

45 of 63 references.

References · 45

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  6. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  7. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  8. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  9. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  10. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  11. 2020Longformer: The Long-Document Transformercited by 3,362
  12. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
33 more
  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  2. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  3. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 888
  4. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 837
  5. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
  6. 2023AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedbackcited by 738
  7. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 721
  8. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 649
  9. 2020Recipes for building an open-domain chatbotcited by 593
  10. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 539
  11. 2016How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generationcited by 356
  12. 2021Beyond Goldfish Memory: Long-Term Open-Domain Conversationcited by 266
  13. 2023L-Eval: Instituting Standardized Evaluation for Long Context Language Modelscited by 232
  14. 2023Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmarkcited by 174
  15. 2023Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERTcited by 155
  16. 2023Towards Making the Most of ChatGPT for Machine Translationcited by 138
  17. 2018Training Millions of Personalized Dialogue Agentscited by 126
  18. 2019Survey on Evaluation Methods for Dialogue Systemscited by 126
  19. 2022Long Time No See! Open-Domain Conversation with Long-Term Persona Memorycited by 107
  20. 2023Guiding Large Language Models via Directional Stimulus Promptingcited by 94
  21. 2023MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversationcited by 94
  22. 2023Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Modelscited by 87
  23. 2023ChatGPT or Grammarly? Evaluating ChatGPT on Grammatical Error Correction Benchmarkcited by 77
  24. 2021Few-Shot Bot: Prompt-Based Learning for Dialogue Systemscited by 64
  25. 2020Memformer: A Memory-Augmented Transformer for Sequence Modelingcited by 63
  26. 2022Keep Me Updated! Memory Management in Long-term Conversationscited by 62
  27. 2023Prompted LLMs as Chatbot Modules for Long Open-domain Conversationcited by 61
  28. 2023SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Promptingcited by 39
  29. 2023Retrieval-Pretrained Transformer: Long-range Language Modeling with Self-retrievalcited by 20
  30. 2023History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue Systemcited by 15
  31. 2023Facilitating Multi-turn Emotional Support Conversation with Positive Emotion Elicitation: A Reinforcement Learning Approachcited by 15
  32. 2021Towards Efficiently Diversifying Dialogue Generation via Embedding Augmentationcited by 9
  33. 2023Effortless Integration of Memory Management into Open-Domain Conversation Systemscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 7; 2025: 18; 2026: 34.

62 papers.

Sort:

By area:

  1. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  2. 2025In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agentscited by 102
  3. 2025On Memory Construction and Retrieval for Personalized Conversational Agentscited by 101
  4. 2024MARG: Multi-Agent Review Generation for Scientific Paperscited by 98
  5. 2025ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inferencecited by 57
  6. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 54
  7. 2023LLMR: Real-time Prompting of Interactive Worlds using Large Language Modelscited by 39
  8. 2024Exploring Autonomous Agents through the Lens of Large Language Models: A Reviewcited by 30
  9. 2025Cognitive Memory in Large Language Modelscited by 28
  10. 2025From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agentscited by 27
  11. 2023Balancing Autonomy and Alignment: A Multi-Dimensional Taxonomy for Autonomous LLM-powered Multi-Agent Architecturescited by 25
  12. 2025Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memorycited by 19
38 more
  1. 2023Empowering Working Memory for Large Language Model Agentscited by 18
  2. 2025Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compressioncited by 16
  3. 2026Evaluating Long-Horizon Memory for Multi-Party Collaborative Dialoguescited by 16
  4. 2025TeleMem: Building Long-Term and Multimodal Memory for Agentic AIcited by 14
  5. 2026Evaluating Memory Structure in LLM Agentscited by 12
  6. 2026VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactionscited by 11
  7. 2025A Survey of Scaling in Large Language Model Reasoningcited by 10
  8. 2025ABBEL: Learning Natural-Language Belief States for Memory-Efficient Interactioncited by 7
  9. 2024Data Analysis in the Era of Generative AIcited by 6
  10. 2025Reasoning or Not? A Comprehensive Evaluation of Reasoning LLMs for Dialogue Summarizationcited by 6
  11. 2026TimeSeriesExamAgent: Creating Time Series Reasoning Benchmarks at Scalecited by 5
  12. 2024Enhancing Long-Term Memory using Hierarchical Aggregate Tree for Retrieval Augmented Generationcited by 4
  13. 2026State Contamination in Memory-Augmented LLM Agentscited by 4
  14. 2025Integrating Counterfactual Simulations with Language Models for Explaining Multi-Agent Behaviourcited by 3
  15. 2026MemGym: a Long-Horizon Memory Environment for LLM Agentscited by 3
  16. 2026Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agentscited by 3
  17. 2024Large Language Models as Realistic Microservice Trace Generatorscited by 2
  18. 2026HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialoguescited by 2
  19. 2024Judgment of Learning: A Human Ability Beyond Generative Artificial Intelligencecited by 1
  20. 2025Efficient On-Device Agents via Adaptive Context Managementcited by 1
  21. 2026HiMeS: Hippocampus-inspired Memory System for Personalized AI Assistantscited by 1
  22. 2026Individual Turing Test: A Case Study of LLM-based Simulation Using Longitudinal Personal Datacited by 1
  23. 2026Context Cartography: Toward Structured Governance of Contextual Space in Large Language Model Systemscited by 1
  24. 2026When Your Agent Opens the Chat App: Agent-Controlled Search over Raw Chat Logs Rivals Structured Memorycited by 1
  25. 2026Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agentscited by 1
  26. 2026Disentangling Long-Term Memory via Latent Neuro-Symbolic Reasoningcited by 1
  27. 2026Decision-Sufficient State Representations: Measuring and Reducing Write-Time Regretcited by 1
  28. 2024Position Debiasing Fine-Tuning for Causal Perception in Long-Term Dialoguecited by 0
  29. 2025Lag-Relative Sparse Attention In Long Context Trainingcited by 0
  30. 2025Conversational No-code, Multi-agentic Disease Module Identification and Drug Repurposing Prediction with ChatDRexcited by 0
  31. 2025DisCEdge: Distributed Context Management for Large Language Models at the Edgecited by 0
  32. 2026Jenius Agent: Towards Experience-Driven Accuracy Optimization in Real-World Scenarioscited by 0
  33. 2026Synthius-Mem: Brain-Inspired Hallucination-Resistant Persona Memory Achieving 94.4% Memory Accuracy and 99.6% Adversarial Robustness on LoCoMocited by 0
  34. 2026Leveraging Weighted Syntactic and Semantic Context Assessment Summary (wSSAS) Towards Text Categorization Using LLMscited by 0
  35. 2026Consistency Analysis of Sentiment Predictions using Syntactic & Semantic Context Assessment Summarization (SSAS)cited by 0
  36. 2026SOMA: Efficient Multi-turn LLM Serving via Small Language Modelcited by 0
  37. 2026BOOKMARKS: Efficient Active Storyline Memory for Role-playingcited by 0
  38. 2026DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Agent Memorycited by 0

50 most cited of 62 All 62 (JSON)