mlsanityData to 7 Oct 2026

MemGPT: Towards LLMs as Operating Systems

arXiv 2310.08560 ↗First posted 12 Oct 2023cs.AIcited by 1,295

Not on the map. Why?

Cited by 751 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Large language models (LLMs) have revolutionized AI, but are constrained by limited context windows, hindering their utility in tasks like extended conversations and document analysis. To enable using context beyond limited context windows, we propose virtual context management, a technique drawing inspiration from hierarchical memory systems in traditional operating systems that provide the appearance of large memory resources through data movement between fast and slow memory. Using this technique, we introduce MemGPT (Memory-GPT), a system that intelligently manages different memory tiers in order to effectively provide extended context within the LLM's limited context window, and utilizes interrupts to manage control flow between itself and the user. We evaluate our OS-inspired design in two domains where the limited context windows of modern LLMs severely handicaps their performance: document analysis, where MemGPT is able to analyze large documents that far exceed the underlying LLM's context window, and multi-session chat, where MemGPT can create conversational agents that remember, reflect, and evolve dynamically through long-term interactions with their users. We release MemGPT code and data for our experiments at https://memgpt.ai.

Key facts. Cited by 1,295 papers in the map (data through 7 Oct 2026). Builds on 35 of its 42 references that are in the map. First posted on arXiv 12 Oct 2023.

Builds on

35 of 42 references.

References · 35

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2022Training language models to follow instructions with human feedbackcited by 15,712
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  7. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  8. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  9. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  10. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  11. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  12. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
23 more
  1. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  2. 2020Longformer: The Long-Document Transformercited by 3,362
  3. 2017Billion-scale similarity search with GPUscited by 2,477
  4. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  5. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
  6. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  7. 2020Reformer: The Efficient Transformercited by 1,658
  8. 2019Generating Long Sequences with Sparse Transformerscited by 1,523
  9. 2020Linformer: Self-Attention with Linear Complexitycited by 1,462
  10. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  11. 2023AgentBench: Evaluating LLMs as Agentscited by 1,211
  12. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  13. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  14. 2021Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolationcited by 1,085
  15. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  16. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 721
  17. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  18. 2023Active Retrieval Augmented Generationcited by 506
  19. 2021Recursively Summarizing Books with Human Feedbackcited by 287
  20. 2021Beyond Goldfish Memory: Long-Term Open-Domain Conversationcited by 266
  21. 2021LongT5: Efficient Text-To-Text Transformer for Long Sequencescited by 232
  22. 2023RA-DIT: Retrieval-Augmented Dual Instruction Tuningcited by 194
  23. 2023A Survey on Long Text Modeling with Transformerscited by 47

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 59; 2025: 160; 2026: 1070.

1,295 papers.

Sort:

By area:

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  2. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,000
  3. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memorycited by 722
  4. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 622
  5. 2025Why Do Multi-Agent LLM Systems Fail?cited by 559
  6. 2024Understanding the planning of LLM agents: A surveycited by 414
  7. 2024LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compressioncited by 343
  8. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 319
  9. 2025Memory in the Age of AI Agentscited by 285
  10. 2025ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memorycited by 253
  11. 2026Meta-Harness: End-to-End Optimization of Model Harnessescited by 248
  12. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactionscited by 236
38 more
  1. 2025Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learningcited by 220
  2. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 206
  3. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 195
  4. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  5. 2024Mooncake: A KVCache-centric Disaggregated Architecture for LLM Servingcited by 193
  6. 2025Survey on Evaluation of LLM-based Agentscited by 190
  7. 2025Multi-agent Architecture Search via Agentic Supernetcited by 164
  8. 2025LightMem: Lightweight and Efficient Memory-Augmented Generationcited by 163
  9. 2025MIRIX: Multi-Agent Memory System for LLM-Based Agentscited by 160
  10. 2024Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fastcited by 149
  11. 2026SimpleMem: Efficient Lifelong Memory for LLM Agentscited by 140
  12. 2025MemOS: A Memory OS for AI Systemcited by 129
  13. 2025Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memorycited by 129
  14. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  15. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  16. 2026SoK: Agentic Skills -- Beyond Tool Use in LLM Agentscited by 120
  17. 2024IsolateGPT: An Execution Isolation Architecture for LLM-Based Agentic Systemscited by 118
  18. 2025Where LLM Agents Fail and How They can Learn From Failurescited by 118
  19. 2023Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systemscited by 101
  20. 2024AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agentscited by 100
  21. 2024AIOS: LLM Agent Operating Systemcited by 94
  22. 2024WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Modelscited by 90
  23. 2025Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solvingcited by 90
  24. 2024A Survey on Self-Evolution of Large Language Modelscited by 86
  25. 2025MemInsight: Autonomous Memory Augmentation for LLM Agentscited by 84
  26. 2026OpenClaw-RL: Train Any Agent Simply by Talkingcited by 83
  27. 2025MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agentscited by 82
  28. 2025PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memorycited by 82
  29. 2025MemEvolve: Meta-Evolution of Agent Memory Systemscited by 81
  30. 2024From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMscited by 77
  31. 2025Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directionscited by 74
  32. 2025Cartridges: Lightweight and general-purpose long context representations via self-studycited by 74
  33. 2023Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Surveycited by 71
  34. 2024Beyond the Limits: A Survey of Techniques to Extend the Context Length in Large Language Modelscited by 71
  35. 2024Retrieval-Augmented Generation for Natural Language Processing: A Surveycited by 70
  36. 2024Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Modelscited by 69
  37. 2025MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Modelscited by 68
  38. 2026Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineeringcited by 68

50 most cited of 1,295 All 1,295 (JSON)