mlsanityData to 7 Oct 2026

Graph-Based Personalized Memory for LLM Agents: Representation, Evolution, Retrieval, and Evaluation

arXiv 2609.08599 ↗First posted 8 Sep 2026cs.AIcited by 0

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

Abstract (arXiv)

Large Language Model (LLM) agents are evolving from single-session tools toward long-term personal assistants that must adapt to individual users across tasks, contexts, and interactions. This shift makes memory a core requirement for personalization, since user preferences, goals, constraints, relationships, and past experiences are accumulated gradually and often change over time. Graph-based personalized memory provides a structured way to model such user information through explicit relations, temporal context, and evidence links. Such representations can model not only what an agent remembers about a user but also how memories are connected, revised, and retrieved to support personalized decisions. However, existing work remains fragmented across personalized agents and generic graph memory frameworks, making it difficult to understand the design space as a whole. This survey develops a lifecycle-oriented view of graph-based personalized memory for LLM agents. We organize existing studies around memory representation, memory evolution, memory retrieval, and memory evaluation. We further compare key design choices, discuss current evaluation practices, and open challenges in building reliable long-term personalized agents. This survey aims to clarify how graph-based memory can support adaptive, controllable, and user-centric LLM agents.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 62 of its 65 references that are in the map. First posted on arXiv 8 Sep 2026.

Builds on

62 of 65 references.

Closest ancestors · 32

Same direction, newest first

  1. 2026Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents4 Jun
  2. 2026EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective18 May
  3. 2026H-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via a Hybrid Structure15 May
  4. 2026PRISM: Pareto-Efficient Retrieval over Intent-Aware Structured Memory for Long-Horizon Agents12 May
  5. 2026HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution11 May
  6. 2026From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms7 May
  7. 2026ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Forgetting5 May
  8. 2026MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents2 May
  9. 2026Hierarchical Long-Term Semantic Memory for LinkedIn's Hiring Agent29 Apr
  10. 2026APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AI15 Apr
  11. 2026GAM: Hierarchical Graph-based Agentic Memory for LLM Agents14 Apr
  12. 2026GAAMA: Graph Augmented Associative Memory for Agents29 Mar
20 more
  1. 2026All-Mem: Agentic Lifelong Memory via Dynamic Topology Evolution20 Mar
  2. 2026Graph-Native Cognitive Memory for AI Agents: Formal Belief Revision Semantics for Versioned Memory Architectures18 Mar
  3. 2026Evaluating Memory Structure in LLM Agents11 Feb
  4. 2026AriadneMem: Threading the Maze of Lifelong Memory for LLM Agents5 Feb
  5. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applications5 Feb
  6. 2026ActMem: Bridging the Gap Between Memory Retrieval and Reasoning in LLM Agents4 Feb
  7. 2026Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation2 Feb
  8. 2026MemWeaver: Weaving Hybrid Memories for Traceable Long-Horizon Agentic Reasoning26 Jan
  9. 2026Bi-Mem: Bidirectional Construction of Hierarchical Memory for Personalized LLMs via Inductive-Reflective Agents10 Jan
  10. 2026MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents6 Jan
  11. 2025PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory7 Dec
  12. 2025LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning3 Nov
  13. 2025RGMem: Renormalization Group-inspired Memory Evolution for Language Agents18 Oct
  14. 2025SGMem: Sentence Graph Memory for Long-Term Conversational Agents25 Sep
  15. 2025What Deserves Memory: Adaptive Memory Distillation for LLM Agents5 Aug
  16. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory28 Apr
  17. 2025Zep: A Temporal Knowledge Graph Architecture for Agent Memory20 Jan
  18. 2024Crafting Personalized Agents through Retrieval-Augmented Generation on Editable Memory Graphs28 Sep
  19. 2024A Survey on the Memory Mechanism of Large Language Model based Agents21 Apr
  20. 2024Evaluating Very Long-Term Conversational Memory of LLM Agents27 Feb

Other references · 30

  1. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  2. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 656
  3. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  4. 2025Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scalecited by 163
  5. 2025On Memory Construction and Retrieval for Personalized Conversational Agentscited by 101
  6. 2025Personalized Generation In Large Model Era: A Surveycited by 45
  7. 2023Personalized Large Language Model Assistant with Evolving Conditional Memorycited by 24
  8. 2026RealMem: Benchmarking LLMs in Real-World Memory-Driven Interactioncited by 20
  9. 2020User Memory Reasoning for Conversational Recommendationcited by 19
  10. 2025Graph-Augmented Large Language Model Agents: Current Progress and Future Prospectscited by 14
  11. 2026HyperMem: Hypergraph Memory for Long-Term Conversationscited by 14
  12. 2026According to Me: Long-Term Personalized Referential Memory QAcited by 12
18 more
  1. 2026Memory in the LLM Era: Modular Architectures and Strategies in a Unified Frameworkcited by 12
  2. 2025Graph Retrieval-Augmented LLM for Conversational Recommendation Systemscited by 10
  3. 2025AssoMem: Scalable Memory QA with Multi-Signal Associative Retrievalcited by 10
  4. 2026Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directionscited by 10
  5. 2025G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledgecited by 9
  6. 2026Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memorycited by 9
  7. 2023Knowledge Graphs and Pre-trained Language Models enhanced Representation Learning for Conversational Recommender Systemscited by 6
  8. 2024Knowledge Graph Tuning: Real-time Large Language Model Personalization based on Human Feedbackcited by 6
  9. 2026EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environmentscited by 5
  10. 2024Reasoning over User Preferences: Knowledge Graph-Augmented LLMs for Explainable Conversational Recommendationscited by 4
  11. 2026MeMo: Memory as a Modelcited by 4
  12. 2025PersonaAgent with GraphRAG: Community-Aware Knowledge Graphs for Personalized LLMcited by 2
  13. 2025LOOM: Personalized Learning Informed by Daily LLM Conversations Toward Long-Term Mastery via a Dynamic Learner Memory Graphcited by 2
  14. 2026HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialoguescited by 2
  15. 2026EngramaBench: Evaluating Long-Term Conversational Memory with Structured Graph Retrievalcited by 2
  16. 2026GRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memorycited by 2
  17. 2026MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Modelscited by 2
  18. 2025DEMENTIA-PLAN: An Agent-Based Framework for Multi-Knowledge Graph Retrieval-Augmented Generation in Dementia Carecited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics
  2. 2026Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
  3. 2025Enabling Personalized Long-term Interactions in LLM-based Agents through Persistent Memory and User Profiles
  4. 2025A-MEM: Agentic Memory for LLM Agents
  5. 2025PersonalAI: A Systematic Comparison of Knowledge Graph Storage and Retrieval Approaches for Personalized LLM agents
  6. 2026Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-horizon Agents
  7. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
  8. 2025From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memory