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

arXiv:2610.10071 · cs.AI · Submitted 2026-10-07 · Read on arXiv

cs.AI

Submitted: 2026-10-07

Updated: 2026-10-07

Code: https://github.com/Ouan6/HGP-

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Agent Memory — 1× in this paper · explained in 1 episode

Sources

• Longformer: The Long-Document Transformer
• Improving language models by retrieving from trillions of tokens
• ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Forgetting
• FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
• FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
• LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
• A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models
• HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
• REALM: Retrieval-Augmented Language Model Pre-Training
• Retrieval-Augmented Generation with Graphs (GraphRAG)
• Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction
• HIRAG: Hierarchical-Thought Instruction-Tuning Retrieval-Augmented Generation
• Memory OS of AI Agent
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• G-Refer: Graph Retrieval-Augmented Large Language Model for Explainable Recommendation
• Lost in the Middle: How Language Models Use Long Contexts
• Evaluating Very Long-Term Conversational Memory of LLM Agents
• RouteLLM: Learning to Route LLMs with Preference Data
• MemGPT: Towards LLMs as Operating Systems

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems