mlsanityData to 14 Oct 2026

On the Structural Memory of LLM Agents

arXiv 2412.15266 ↗First posted 17 Dec 2024cs.CL cs.AIcited by 37

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

Abstract (arXiv)

Memory plays a pivotal role in enabling large language model~(LLM)-based agents to engage in complex and long-term interactions, such as question answering (QA) and dialogue systems. While various memory modules have been proposed for these tasks, the impact of different memory structures across tasks remains insufficiently explored. This paper investigates how memory structures and memory retrieval methods affect the performance of LLM-based agents. Specifically, we evaluate four types of memory structures, including chunks, knowledge triples, atomic facts, and summaries, along with mixed memory that combines these components. In addition, we evaluate three widely used memory retrieval methods: single-step retrieval, reranking, and iterative retrieval. Extensive experiments conducted across four tasks and six datasets yield the following key insights: (1) Different memory structures offer distinct advantages, enabling them to be tailored to specific tasks; (2) Mixed memory structures demonstrate remarkable resilience in noisy environments; (3) Iterative retrieval consistently outperforms other methods across various scenarios. Our investigation aims to inspire further research into the design of memory systems for LLM-based agents.

Key facts. Cited by 37 papers in the map (data through 14 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 28 of its 43 references that are in the map. First posted on arXiv 17 Dec 2024.

Builds on

28 of 43 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024A Survey on the Memory Mechanism of Large Language Model based Agents21 Apr
  2. 2024Evaluating Very Long-Term Conversational Memory of LLM Agents27 Feb
  3. 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts15 Feb

Other references · 25

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  4. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  5. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  6. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  7. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  8. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  9. 2023LongBench: A Bilingual, Multitask Benchmark for Long Context Understandingcited by 1,417
  10. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  11. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  12. 2023ChatDev: Communicative Agents for Software Developmentcited by 919
13 more
  1. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  2. 2021Learning To Retrieve Prompts for In-Context Learningcited by 648
  3. 2017The NarrativeQA Reading Comprehension Challengecited by 597
  4. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  5. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 212
  6. 2021QuALITY: Question Answering with Long Input Texts, Yes!cited by 208
  7. 2023InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviewscited by 179
  8. 2024Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimizationcited by 94
  9. 2023MetaAgents: Large Language Model Based Agents for Decision-Making on Teamingcited by 85
  10. 2024Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answeringcited by 51
  11. 2024Don't Forget to Connect! Improving RAG with Graph-based Rerankingcited by 49
  12. 2024CorpusLM: Towards a Unified Language Model on Corpus for Knowledge-Intensive Taskscited by 18
  13. 2024TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generationcited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 18; 2026: 19.

37 papers.

Sort:

By area:

  1. 2025Memory Injection Attacks on LLM Agents via Query-Only Interactioncited by 144
  2. 2025A Survey of Context Engineering for Large Language Modelscited by 126
  3. 2025How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behaviorcited by 101
  4. 2025Towards Scientific Intelligence: A Survey of LLM-based Scientific Agentscited by 98
  5. 2025Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solvingcited by 94
  6. 2025EvoAgentX: An Automated Framework for Evolving Agentic Workflowscited by 44
  7. 2025MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learningcited by 27
  8. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applicationscited by 25
  9. 2025Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunitiescited by 23
  10. 2026Self-Improvements in Modern Agentic Systems: A Surveycited by 19
  11. 2025The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systemscited by 14
  12. 2025MEMTRACK: Evaluating Long-Term Memory and State Tracking in Multi-Platform Dynamic Agent Environmentscited by 13
25 more
  1. 2025On the Failure of Latent State Persistence in Large Language Modelscited by 9
  2. 2026Gated Differentiable Working Memory for Long-Context Language Modelingcited by 6
  3. 2025A Survey of Foundation Models for IoT: Taxonomy and Criteria-Based Analysiscited by 5
  4. 2026Aligning Agentic World Models via Knowledgeable Experience Learningcited by 5
  5. 2026MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agentscited by 5
  6. 2026Learning to Retrieve: Dual-Level Long-Term Memory for Text-to-SQL Agentscited by 4
  7. 2025MARK: Memory Augmented Refinement of Knowledgecited by 3
  8. 2025Can Past Experience Accelerate LLM Reasoning?cited by 3
  9. 2025A Principle-based Framework for the Development and Evaluation of Large Language Models for Health and Wellnesscited by 3
  10. 2026Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agentscited by 3
  11. 2025Training-Free Multimodal Large Language Model Orchestrationcited by 2
  12. 2026Benchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generationcited by 2
  13. 2026From Agent Loops to Deterministic Graphs: Execution Lineage for Reproducible AI-Native Workcited by 2
  14. 2025Fidelity Before Structure: Verbatim Chunks Beat Lossy Artifact Extraction in Long-Conversation LLM Memorycited by 1
  15. 2026MetaEvo: A Meta-Optimization Framework for Experience-Driven Agent Evolutioncited by 1
  16. 2026A Technical Taxonomy of LLM Agent Communication Protocolscited by 1
  17. 2026Dual-Layer Agentic Memory with Fast Write Routing and Slow Consolidationcited by 1
  18. 2026When Does Selection Replace Extraction? A Pre-Registered Test of Agent Memory with a Typed Decision Modelcited by 1
  19. 2025GoalfyMax: A Protocol-Driven Multi-Agent System for Intelligent Experience Entitiescited by 0
  20. 2026ACF: A Collaborative Framework for Agent Covert Communication under Cognitive Asymmetrycited by 0
  21. 2026Fine-Tuning Small Language Models for Solution-Oriented Windows Event Log Analysiscited by 0
  22. 2026MemPrism: Task-Conditioned Relational Memory Views for Long-Horizon Agentscited by 0
  23. 2026SkillSmith: Enhancing Locally Deployed Agents via Automatic Skill Construction and Evolutioncited by 0
  24. 2026What Makes Agent Memory Useful for Reliable Unanswerable Question Handling?cited by 0
  25. 2026MoM: Memory of Memorycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics
  2. 2026Evaluating Memory Structure in LLM Agents
  3. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
  4. 2026Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
  5. 2025Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents
  6. 2025A-MEM: Agentic Memory for LLM Agents
  7. 2026H-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via a Hybrid Structure
  8. 2026AMA: Adaptive Memory via Multi-Agent Collaboration