mlsanityData to 14 Oct 2026

Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents

arXiv 2507.22925 ↗First posted 23 Jul 2025cs.CL cs.AIcited by 62

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

also in 1 more
Abstract (arXiv)

Long-term memory is one of the key factors influencing the reasoning capabilities of Large Language Model Agents (LLM Agents). Incorporating a memory mechanism that effectively integrates past interactions can significantly enhance decision-making and contextual coherence of LLM Agents. While recent works have made progress in memory storage and retrieval, such as encoding memory into dense vectors for similarity-based search or organizing knowledge in the form of graph, these approaches often fall short in structured memory organization and efficient retrieval. To address these limitations, we propose a Hierarchical Memory (H-MEM) architecture for LLM Agents that organizes and updates memory in a multi-level fashion based on the degree of semantic abstraction. Each memory vector is embedded with a positional index encoding pointing to its semantically related sub-memories in the next layer. During the reasoning phase, an index-based routing mechanism enables efficient, layer-by-layer retrieval without performing exhaustive similarity computations. We evaluate our method on five task settings from the LoCoMo dataset. Experimental results show that our approach consistently outperforms five baseline methods, demonstrating its effectiveness in long-term dialogue scenarios.

Key facts. Cited by 62 papers in the map (data through 14 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 16 of its 23 references that are in the map. First posted on arXiv 23 Jul 2025.

Builds on

16 of 23 references.

References · 16

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  2. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2024Qwen2 Technical Reportcited by 2,120
  5. 2024A Survey on LLM-as-a-Judgecited by 1,423
  6. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,063
  7. 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 830
  8. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 634
  9. 2024Understanding the planning of LLM agents: A surveycited by 421
  10. 2024The Faiss librarycited by 376
  11. 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Securitycited by 260
  12. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
4 more
  1. 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contextscited by 146
  2. 2023SCM: Enhancing Large Language Model with Self-Controlled Memory Frameworkcited by 98
  3. 2025MemInsight: Autonomous Memory Augmentation for LLM Agentscited by 85
  4. 2024LLM With Tools: A Surveycited by 61

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 10; 2026: 52.

62 papers.

Sort:

By area:

  1. 2025MemEvolve: Meta-Evolution of Agent Memory Systemscited by 95
  2. 2026EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoningcited by 54
  3. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 44
  4. 2026HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understandingcited by 41
  5. 2025LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automationcited by 40
  6. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applicationscited by 25
  7. 2025Preference-Aware Memory Update for Long-Term LLM Agentscited by 20
  8. 2026Self-Improvements in Modern Agentic Systems: A Surveycited by 19
  9. 2025Context Engineering 2.0: The Context of Context Engineeringcited by 18
  10. 2026Memory Matters More: Event-Centric Memory as a Logic Map for Agent Searching and Reasoningcited by 17
  11. 2026APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AIcited by 17
  12. 2026Toward Efficient Agents: Memory, Tool learning, and Planningcited by 16
38 more
  1. 2026Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agentscited by 14
  2. 2025AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agentscited by 12
  3. 2026Evaluating Memory Structure in LLM Agentscited by 12
  4. 2026Memory in the LLM Era: Modular Architectures and Strategies in a Unified Frameworkcited by 12
  5. 2025Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AIcited by 8
  6. 2026Semantic XPath: Structured Agentic Memory Access for Conversational AIcited by 7
  7. 2026Agentic Trading: When LLM Agents Meet Financial Marketscited by 7
  8. 2025Learning from Supervision with Semantic and Episodic Memory: A Reflective Approach to Agent Adaptationcited by 6
  9. 2025ReflecSched: Solving Dynamic Flexible Job-Shop Scheduling via LLM-Powered Hierarchical Reflectioncited by 5
  10. 2025See, Think, Act: Online Shopper Behavior Simulation with VLM Agentscited by 5
  11. 2026Toward a Theory of Hierarchical Memory for Language Agentscited by 5
  12. 2026HiGMem: A Hierarchical and LLM-Guided Memory System for Long-Term Conversational Agentscited by 5
  13. 2026Mitigating Provenance-Role Collapse in Long-Term Agents via Typed Memory Representationcited by 5
  14. 2026LazyMem: Retrieve Broadly, Construct Selectively for Efficient Long-Term Agent Memorycited by 5
  15. 2026ES-Mem: Event Segmentation-Based Memory for Long-Term Dialogue Agentscited by 4
  16. 2026CarePilot: A Multi-Agent Framework for Long-Horizon Computer Task Automation in Healthcarecited by 4
  17. 2026Learning to Retrieve: Dual-Level Long-Term Memory for Text-to-SQL Agentscited by 4
  18. 2026From Atom to Community: Structured and Evolving Agent Memory for User Behavior Modelingcited by 3
  19. 2026BMAM: Brain-inspired Multi-Agent Memory Frameworkcited by 3
  20. 2026MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoningcited by 3
  21. 2026Zero-Mem: Zero-Token Memory Operations for LLM Agentscited by 3
  22. 2026Mitigating Over-Personalization in LLMs via Structured Memorycited by 3
  23. 2026TraceMem: Weaving Narrative Memory Schemata from User Conversational Tracescited by 2
  24. 2026Learning to Reason with Insight for Informal Theorem Provingcited by 2
  25. 2026Simulating Human Memory with Language Modelscited by 2
  26. 2025The Imperfect Learner: Incorporating Developmental Trajectories in Memory-based Student Simulationcited by 1
  27. 2026Enhancing Conversational Agents via Task-Oriented Adversarial Memory Adaptationcited by 1
  28. 2026Four-Axis Decision Alignment for Long-Horizon Enterprise AI Agentscited by 1
  29. 2026MEMTIER: Tiered Memory Architecture and Retrieval Bottleneck Analysis for Long-Running Autonomous AI Agentscited by 1
  30. 2026DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Agent Memorycited by 1
  31. 2026SubtleMemory: A Benchmark for Fine-Grained Relational Memory Discrimination in Long-Horizon AI Agentscited by 1
  32. 2026Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agentscited by 1
  33. 2026Memory Control Signals Emerge Before Action in Long Horizon Agentscited by 1
  34. 2026Back to Basics: Let Conversational Agents Remember with Just Retrieval and Generationcited by 0
  35. 2026Retention Consequence in Lifecycle Memory Controlcited by 0
  36. 2026Stateless Decision Memory for Enterprise AI Agentscited by 0
  37. 2026Enhancing Software Engineering Through Closed-Loop Memory Optimizationcited by 0
  38. 2026Rosetta Memory: Adaptive Memory for Cross-LLM Agentscited by 0

50 most cited of 62 All 62 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning
  2. 2024On the Structural Memory of LLM Agents
  3. 2026Accurate and Efficient Long-Term Memory for LLM Agents
  4. 2026Weighted Memory Tree: Remembering What Matters for Long-Horizon LLM Agents
  5. 2026SF-AMS: Strategic Forgetting for Structured Memory in LLM Agent
  6. 2026StructMem: Structured Memory for Long-Horizon Behavior in LLMs
  7. 2026MemWeaver: Weaving Hybrid Memories for Traceable Long-Horizon Agentic Reasoning
  8. 2026GAM: Hierarchical Graph-based Agentic Memory for LLM Agents