mlsanityData to 7 Oct 2026

HGP:An on-device personalized agent memory via hybrid graph storage

arXiv 2610.10071 ↗First posted 7 Oct 2026cs.AIcited by 0

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

Abstract (arXiv)

LLM-based agents face challenges in personalized interactive tasks due to heterogeneous, multi-typed, and implicitly constrained long-term traces. Existing memory mechanisms struggle with accurate routing and retrieval, especially on-device where personalization is critical. Most methods use single-vector representations, blurring type distinctions and relational structure. We propose HGP, a hybrid graph memory framework. HGP employs a lightweight self-enhancement classifier for personalized memory routing and constructs episodic, semantic, and procedural memories as graphs. It also extracts working memory as a state trajectory to capture current state and implicit constraints, ensuring reliable decision-making. The classifier reduces large-model calls, enabling on-device deployment, while graph storage enables accurate retrieval and incremental user profile refinement. Experiments on two benchmarks show that on PAL-Set solution selection, HGP achieves an S-score of 35.58, nearly 7 points above the strongest baseline. Code and data are at https://github.com/Ouan6/HGP-.git.

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 34 of its 41 references that are in the map. First posted on arXiv 7 Oct 2026.

Builds on

34 of 41 references.

Closest ancestors · 8

Same direction, newest first

  1. 2026ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Forgetting5 May
  2. 2026PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents6 Feb
  3. 2025Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction17 Nov
  4. 2025G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems9 Jun
  5. 2025Memory OS of AI Agent30 May
  6. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory28 Apr
  7. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
  8. 2024Evaluating Very Long-Term Conversational Memory of LLM Agents27 Feb

Other references · 26

  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. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  4. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  5. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  6. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  7. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  8. 2020Longformer: The Long-Document Transformercited by 3,362
  9. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  10. 2020Big Bird: Transformers for Longer Sequencescited by 1,673
  11. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  12. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
14 more
  1. 2021Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolationcited by 1,085
  2. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 791
  3. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 633
  4. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 539
  5. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 450
  6. 2023Cognitive Architectures for Language Agentscited by 422
  7. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  8. 2024LongRoPE: Extending LLM Context Window Beyond 2 Million Tokenscited by 302
  9. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 273
  10. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
  11. 2023Large Language Models as Topological Structure Enhancers for Text-Attributed Graphscited by 27
  12. 2025G-Refer: Graph Retrieval-Augmented Large Language Model for Explainable Recommendationcited by 26
  13. 2025LeanRAG: Knowledge-Graph-Based Generation with Semantic Aggregation and Hierarchical Retrievalcited by 14
  14. 2025HIRAG: Hierarchical-Thought Instruction-Tuning Retrieval-Augmented Generationcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Graph-Based Personalized Memory for LLM Agents: Representation, Evolution, Retrieval, and Evaluation
  2. 2026Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-horizon Agents
  3. 2026MemAgent: Learning to Manage Heterogeneous Memory Providers for LLM Agents
  4. 2024Crafting Personalized Agents through Retrieval-Augmented Generation on Editable Memory Graphs
  5. 2026Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline
  6. 2026Hybrid Self-evolving Structured Memory for GUI Agents
  7. 2025Efficient On-Device Agents via Adaptive Context Management
  8. 2026HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution