mlsanityData to 7 Oct 2026

MemInsight: Autonomous Memory Augmentation for LLM Agents

arXiv 2503.21760 ↗First posted 27 Mar 2025cs.CLcited by 84

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

Abstract (arXiv)

Large language model (LLM) agents have evolved to intelligently process information, make decisions, and interact with users or tools. A key capability is the integration of long-term memory capabilities, enabling these agents to draw upon historical interactions and knowledge. However, the growing memory size and need for semantic structuring pose significant challenges. In this work, we propose an autonomous memory augmentation approach, MemInsight, to enhance semantic data representation and retrieval mechanisms. By leveraging autonomous augmentation to historical interactions, LLM agents are shown to deliver more accurate and contextualized responses. We empirically validate the efficacy of our proposed approach in three task scenarios; conversational recommendation, question answering and event summarization. On the LLM-REDIAL dataset, MemInsight boosts persuasiveness of recommendations by up to 14%. Moreover, it outperforms a RAG baseline by 34% in recall for LoCoMo retrieval. Our empirical results show the potential of MemInsight to enhance the contextual performance of LLM agents across multiple tasks.

Key facts. Cited by 84 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 20 of its 29 references that are in the map. First posted on arXiv 27 Mar 2025.

Builds on

20 of 29 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
  2. 2025TReMu: Towards Neuro-Symbolic Temporal Reasoning for LLM-Agents with Memory in Multi-Session Dialogues3 Feb
  3. 2024A Survey on the Memory Mechanism of Large Language Model based Agents21 Apr
  4. 2024"My agent understands me better": Integrating Dynamic Human-like Memory Recall and Consolidation in LLM-Based Agents31 Mar
  5. 2024Evaluating Very Long-Term Conversational Memory of LLM Agents27 Feb
  6. 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts15 Feb

Other references · 14

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  3. 2017Billion-scale similarity search with GPUscited by 2,477
  4. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  5. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  6. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  7. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 814
  8. 2024Mixture-of-Agents Enhances Large Language Model Capabilitiescited by 420
  9. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 288
  10. 2023ChatDB: Augmenting LLMs with Databases as Their Symbolic Memorycited by 136
  11. 2024Online Adaptation of Language Models with a Memory of Amortized Contextscited by 35
  12. 2024Can Large Multimodal Models Uncover Deep Semantics Behind Images?cited by 16
2 more
  1. 2025Self-Evolving Critique Abilities in Large Language Modelscited by 12
  2. 2024Bridging Search and Recommendation in Generative Retrieval: Does One Task Help the Other?cited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 18; 2026: 66.

84 papers.

Sort:

By area:

  1. 2025Memory in the Age of AI Agentscited by 285
  2. 2025Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learningcited by 220
  3. 2025LightMem: Lightweight and Efficient Memory-Augmented Generationcited by 163
  4. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 155
  5. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  6. 2025Memento: Fine-tuning LLM Agents without Fine-tuning LLMscited by 119
  7. 2026MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memorycited by 113
  8. 2025G-Memory: Tracing Hierarchical Memory for Multi-Agent Systemscited by 112
  9. 2026AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolutioncited by 105
  10. 2025Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solvingcited by 90
  11. 2026Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agentscited by 72
  12. 2025Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agentscited by 60
38 more
  1. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  2. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 40
  3. 2025Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topicscited by 36
  4. 2025Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Taskscited by 22
  5. 2026ReCreate: Reasoning and Creating Domain Agents Driven by Experiencecited by 22
  6. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applicationscited by 22
  7. 2026From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flawscited by 21
  8. 2025Preference-Aware Memory Update for Long-Term LLM Agentscited by 19
  9. 2026From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanismscited by 19
  10. 2026HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agentscited by 16
  11. 2026Evaluating Long-Horizon Memory for Multi-Party Collaborative Dialoguescited by 16
  12. 2026APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AIcited by 16
  13. 2026HyperMem: Hypergraph Memory for Long-Term Conversationscited by 14
  14. 2026EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspectivecited by 14
  15. 2025MEMTRACK: Evaluating Long-Term Memory and State Tracking in Multi-Platform Dynamic Agent Environmentscited by 13
  16. 2026Agentic Artificial Intelligence (AI): Architectures, Taxonomies, and Evaluation of Large Language Model Agentscited by 11
  17. 2026Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directionscited by 10
  18. 2025Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AIcited by 8
  19. 2026LifeBench: A Benchmark for Long-Horizon Multi-Source Memorycited by 8
  20. 2026Darwinian Memory: A Training-Free Self-Regulating Memory System for GUI Agent Evolutioncited by 7
  21. 2025Learning from Supervision with Semantic and Episodic Memory: A Reflective Approach to Agent Adaptationcited by 6
  22. 2026Gated Differentiable Working Memory for Long-Context Language Modelingcited by 6
  23. 2026AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignmentcited by 6
  24. 2025Smarter Together: Creating Agentic Communities of Practice through Shared Experiential Learningcited by 5
  25. 2026Aligning Agentic World Models via Knowledgeable Experience Learningcited by 5
  26. 2026AutoAgent: Evolving Cognition and Elastic Memory Orchestration for Adaptive Agentscited by 5
  27. 2026Complementary RL: Towards Efficient Experience-Driven Agent Learningcited by 5
  28. 2026Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMscited by 4
  29. 2026Your Code Agent Can Grow Alongside You with Structured Memorycited by 4
  30. 2026Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interactioncited by 4
  31. 2026Learning to Retrieve: Dual-Level Long-Term Memory for Text-to-SQL Agentscited by 4
  32. 2025Cognitive Weave: Synthesizing Abstracted Knowledge with a Spatio-Temporal Resonance Graphcited by 3
  33. 2026Agent Skill Framework: Perspectives on the Potential of Small to Medium Language Models in Industrial Environmentscited by 3
  34. 2026M2: Dual-Memory Augmentation for Long-Horizon Web Agents via Trajectory Summarization and Insight Retrievalcited by 3
  35. 2026Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memorycited by 3
  36. 2026MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agentscited by 3
  37. 2026Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agentscited by 3
  38. 2026Self-evolving Embodied AIcited by 2

50 most cited of 84 All 84 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026TA-Mem: Tool-Augmented Autonomous Memory Retrieval for LLM in Long-Term Conversational QA
  2. 2026Towards Autonomous Memory Agents
  3. 2026MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents
  4. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
  5. 2026Lightweight LLM Agent Memory with Small Language Models
  6. 2026MemToolAgent: Leveraging Memory for Tool Using Agents Based on Environment and User Feedback
  7. 2026Evaluating Memory Structure in LLM Agents
  8. 2024On the Structural Memory of LLM Agents