mlsanityData to 7 Oct 2026

E-mem: Multi-agent based Episodic Context Reconstruction for LLM Agent Memory

arXiv 2601.21714 ↗First posted 29 Jan 2026cs.AIcited by 10

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 1 more
Abstract (arXiv)

The evolution of Large Language Model (LLM) agents towards System~2 reasoning, characterized by deliberative, high-precision problem-solving, requires maintaining rigorous logical integrity over extended horizons. However, prevalent memory preprocessing paradigms suffer from destructive de-contextualization. By compressing complex sequential dependencies into pre-defined structures (e.g., embeddings or graphs), these methods sever the contextual integrity essential for deep reasoning. To address this, we propose E-mem, a framework shifting from Memory Preprocessing to Episodic Context Reconstruction. Inspired by biological engrams, E-mem employs a heterogeneous hierarchical architecture where multiple assistant agents maintain uncompressed memory contexts, while a central master agent orchestrates global planning. Unlike passive retrieval, our mechanism empowers assistants to locally reason within activated segments, extracting context-aware evidence before aggregation. Evaluations on the LoCoMo benchmark demonstrate that E-mem achieves over 54% F1, surpassing the state-of-the-art GAM by 7.75%, while reducing token cost by over 70%.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 30 of its 41 references that are in the map. First posted on arXiv 29 Jan 2026.

Builds on

30 of 41 references.

References · 30

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  7. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  8. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  9. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  10. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  11. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  12. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
18 more
  1. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  2. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  3. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,000
  4. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  5. 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 800
  6. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memorycited by 722
  7. 2022Automatic Chain of Thought Prompting in Large Language Modelscited by 684
  8. 2023Active Retrieval Augmented Generationcited by 506
  9. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 273
  10. 2022Recurrent Memory Transformercited by 197
  11. 2025LightMem: Lightweight and Efficient Memory-Augmented Generationcited by 163
  12. 2025Memory OS of AI Agentcited by 140
  13. 2023ChatDB: Augmenting LLMs with Databases as Their Symbolic Memorycited by 136
  14. 2025G-Memory: Tracing Hierarchical Memory for Multi-Agent Systemscited by 112
  15. 2024AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agentscited by 100
  16. 2024AIOS: LLM Agent Operating Systemcited by 94
  17. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 78
  18. 2025MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systemscited by 56

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 10.

10 papers.

  1. 2026Governing Evolving Memory in LLM Agents: Risks, Mechanisms, and the Stability and Safety Governed Memory (SSGM) Frameworkcited by 16
  2. 2026Graph-Native Cognitive Memory for AI Agents: Formal Belief Revision Semantics for Versioned Memory Architecturescited by 9
  3. 2026D-Mem: A Dual-Process Memory System for LLM Agentscited by 5
  4. 2026Stop When Memory Suffices: Evidence-Conditioned Progressive Execution for LLM Agentscited by 2
  5. 2026Context Cartography: Toward Structured Governance of Contextual Space in Large Language Model Systemscited by 1
  6. 2026MESA:Task-Adaptive Multi-Structure Evidence Selection for Long-Horizon Agent Memorycited by 1
  7. 2026Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligencecited by 1
  8. 2026Activity Frames: Deterministic Screen-Activity Compilation for Agent Memory and Replaycited by 0
  9. 2026Topological Coherence for Self-evolving Multi-agent Systemscited by 0
  10. 2026NativeScope: Relation-Localized Retrieval over Native Topology with a Correct Anchorcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026MemWeaver: Weaving Hybrid Memories for Traceable Long-Horizon Agentic Reasoning
  2. 2026Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents
  3. 2026ContextWeaver: Selective and Dependency-Structured Memory Construction for LLM Agents
  4. 2026REMem: Reasoning with Episodic Memory in Language Agent
  5. 2026GAM: Hierarchical Graph-based Agentic Memory for LLM Agents
  6. 2026EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning
  7. 2025Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memory
  8. 2026Episodic-Semantic Memory Architecture for Long-Horizon Scientific Agents