mlsanityData to 7 Oct 2026

Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents

arXiv 2502.06975 ↗First posted 10 Feb 2025cs.AIcited by 35

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

Abstract (arXiv)

As Large Language Models (LLMs) evolve from text-completion tools into fully fledged agents operating in dynamic environments, they must address the challenge of continually learning and retaining long-term knowledge. Many biological systems solve these challenges with episodic memory, which supports single-shot learning of instance-specific contexts. Inspired by this, we present an episodic memory framework for LLM agents, centered around five key properties of episodic memory that underlie adaptive and context-sensitive behavior. With various research efforts already partially covering these properties, this position paper argues that now is the right time for an explicit, integrated focus on episodic memory to catalyze the development of long-term agents. To this end, we outline a roadmap that unites several research directions under the goal to support all five properties of episodic memory for more efficient long-term LLM agents.

Key facts. Cited by 35 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 69 of its 113 references that are in the map. First posted on arXiv 10 Feb 2025.

Builds on

69 of 113 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory7 Feb

Other references · 68

  1. 2020Scaling Laws for Neural Language Modelscited by 6,411
  2. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  3. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  4. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  5. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  6. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  7. 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,107
  8. 2022Mass-Editing Memory in a Transformercited by 976
  9. 2023RWKV: Reinventing RNNs for the Transformer Eracited by 814
  10. 2014Neural Turing Machinescited by 630
  11. 2024KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cachecited by 604
  12. 2023Enabling Large Language Models to Generate Text with Citationscited by 584
38 more
  1. 2024KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantizationcited by 571
  2. 2021Editing Factual Knowledge in Language Modelscited by 548
  3. 2023Model Tells You What to Discard: Adaptive KV Cache Compression for LLMscited by 466
  4. 2022Memory-Based Model Editing at Scalecited by 443
  5. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 405
  6. 2023The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"cited by 399
  7. 2024Learning to (Learn at Test Time): RNNs with Expressive Hidden Statescited by 329
  8. 2024Graph Retrieval-Augmented Generation: A Surveycited by 320
  9. 2024Titans: Learning to Memorize at Test Timecited by 303
  10. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 273
  11. 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Securitycited by 257
  12. 2024InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Managementcited by 242
  13. 2022Recurrent Memory Transformercited by 197
  14. 2024ReFT: Representation Finetuning for Language Modelscited by 186
  15. 2024Do Large Language Models Latently Perform Multi-Hop Reasoning?cited by 165
  16. 2024PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inferencecited by 148
  17. 2024You Only Cache Once: Decoder-Decoder Architectures for Language Modelscited by 135
  18. 2022Learning by Distilling Contextcited by 128
  19. 2015Large-scale Simple Question Answering with Memory Networkscited by 127
  20. 2024Reducing Transformer Key-Value Cache Size with Cross-Layer Attentioncited by 122
  21. 2024MiniCache: KV Cache Compression in Depth Dimension for Large Language Modelscited by 122
  22. 2024The Mamba in the Llama: Distilling and Accelerating Hybrid Modelscited by 120
  23. 2024Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inferencecited by 115
  24. 2022Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning Systemcited by 110
  25. 2024RazorAttention: Efficient KV Cache Compression Through Retrieval Headscited by 99
  26. 2023SCM: Enhancing Large Language Model with Self-Controlled Memory Frameworkcited by 98
  27. 2023MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversationcited by 94
  28. 2024Model Editing at Scale leads to Gradual and Catastrophic Forgettingcited by 92
  29. 2024WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Modelscited by 90
  30. 2024Long-Context Language Modeling with Parallel Context Encodingcited by 84
  31. 2024ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partitioncited by 81
  32. 2023MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRAcited by 80
  33. 2024Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCachecited by 71
  34. 2024WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains Morecited by 69
  35. 2023Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memorycited by 64
  36. 2023Massive Editing for Large Language Models via Meta Learningcited by 62
  37. 2024Human-inspired Episodic Memory for Infinite Context LLMscited by 62
  38. 2024LoFiT: Localized Fine-tuning on LLM Representationscited by 56

50 most cited of 68 All 68 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 13; 2026: 22.

35 papers.

Sort:

By area:

  1. 2025MIRIX: Multi-Agent Memory System for LLM-Based Agentscited by 160
  2. 2025Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solvingcited by 90
  3. 2025Embodied AI Agents: Modeling the Worldcited by 57
  4. 2025Mem-α: Learning Memory Construction via Reinforcement Learningcited by 49
  5. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 40
  6. 2025Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topicscited by 36
  7. 2026Hidden in Memory: Sleeper Memory Poisoning in LLM Agentscited by 22
  8. 2025AI Scientists Fail Without Strong Implementation Capabilitycited by 20
  9. 2026Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agentscited by 18
  10. 2026Trajectory-Informed Memory Generation for Self-Improving Agent Systemscited by 16
  11. 2025The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systemscited by 14
  12. 2025CLiViS: Unleashing Cognitive Map through Linguistic-Visual Synergy for Embodied Visual Reasoningcited by 13
23 more
  1. 2025Review of Case-Based Reasoning for LLM Agents: Theoretical Foundations, Architectural Components, and Cognitive Integrationcited by 12
  2. 2025IMPersona: Evaluating Individual Level LM Impersonationcited by 11
  3. 2026Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directionscited by 10
  4. 2025Memory-Augmented Transformers: A Systematic Review from Neuroscience Principles to Enhanced Model Architecturescited by 9
  5. 2026Position: Modular Memory is the Key to Continual Learning Agentscited by 7
  6. 2026Gated Differentiable Working Memory for Long-Context Language Modelingcited by 6
  7. 2026LMEB: Long-horizon Memory Embedding Benchmarkcited by 6
  8. 2026MemCollab: Cross-Model Memory Collaboration via Contrastive Trajectory Distillationcited by 6
  9. 2026Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agentscited by 6
  10. 2026RaMem: Contextual Reinstatement for Long-term Agentic Memorycited by 5
  11. 2026Memory poisoning and secure multi-agent systemscited by 4
  12. 2026Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMscited by 3
  13. 2026M2: Dual-Memory Augmentation for Long-Horizon Web Agents via Trajectory Summarization and Insight Retrievalcited by 3
  14. 2026MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agentscited by 3
  15. 2026AgentKVShift: Efficient KV Cache Reuse for Agentic Memory Systemscited by 2
  16. 2025Applying Cognitive Design Patterns to General LLM Agentscited by 1
  17. 2026Attention Is Not Retention: The Orthogonality Constraint in Infinite-Context Architecturescited by 1
  18. 2026CraniMem: Cranial Inspired Gated and Bounded Memory for Agentic Systemscited by 1
  19. 2026Context Cartography: Toward Structured Governance of Contextual Space in Large Language Model Systemscited by 1
  20. 2026SEAM: Shot Entity-Attribute Memory for Consistent Short-Drama Generation at Scalecited by 1
  21. 2025Towards Reliable Multi-Agent Systems for Marketing Applications via Reflection, Memory, and Planningcited by 0
  22. 2026Activity Frames: Deterministic Screen-Activity Compilation for Agent Memory and Replaycited by 0
  23. 2026The Epistemics of Agent Memory: Measuring, and Governing, the Consolidation Decision in Long-Horizon LLM Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
  2. 2024A Survey on the Memory Mechanism of Large Language Model based Agents
  3. 2026Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
  4. 2026Verifiable Memory: Learning Unified Memory Management with Local and Global Verifiers for Large Language Model Agents
  5. 2026PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning
  6. 2026Continuum Memory Architectures for Long-Horizon LLM Agents
  7. 2023Empowering Working Memory for Large Language Model Agents
  8. 2026Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents