mlsanityData to 7 Oct 2026

Crafting Personalized Agents through Retrieval-Augmented Generation on Editable Memory Graphs

arXiv 2409.19401 ↗First posted 28 Sep 2024cs.CL cs.IRcited by 38

On the map: Retrieval-augmented generation → Agentic RAG, agents and memory

also in 1 more
Abstract (arXiv)

In the age of mobile internet, user data, often referred to as memories, is continuously generated on personal devices. Effectively managing and utilizing this data to deliver services to users is a compelling research topic. In this paper, we introduce a novel task of crafting personalized agents powered by large language models (LLMs), which utilize a user's smartphone memories to enhance downstream applications with advanced LLM capabilities. To achieve this goal, we introduce EMG-RAG, a solution that combines Retrieval-Augmented Generation (RAG) techniques with an Editable Memory Graph (EMG). This approach is further optimized using Reinforcement Learning to address three distinct challenges: data collection, editability, and selectability. Extensive experiments on a real-world dataset validate the effectiveness of EMG-RAG, achieving an improvement of approximately 10% over the best existing approach. Additionally, the personalized agents have been transferred into a real smartphone AI assistant, which leads to enhanced usability.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation. Builds on 29 of its 47 references that are in the map. First posted on arXiv 28 Sep 2024.

Builds on

29 of 47 references.

References · 29

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  3. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  4. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,026
  5. 2022Mass-Editing Memory in a Transformercited by 976
  6. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
  7. 2021Editing Factual Knowledge in Language Modelscited by 548
  8. 2021Fast Model Editing at Scalecited by 491
  9. 2022Memory-Based Model Editing at Scalecited by 443
  10. 2022Text and Code Embeddings by Contrastive Pre-Trainingcited by 358
  11. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  12. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
17 more
  1. 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Securitycited by 257
  2. 2023PMET: Precise Model Editing in a Transformercited by 170
  3. 2022REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memorycited by 122
  4. 2021Case-based Reasoning for Natural Language Queries over Knowledge Basescited by 107
  5. 2022Long Time No See! Open-Domain Conversation with Long-Term Persona Memorycited by 107
  6. 2021RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answeringcited by 86
  7. 2020You Impress Me: Dialogue Generation via Mutual Persona Perceptioncited by 85
  8. 2021BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Datacited by 75
  9. 2023Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM's Translation Capabilitycited by 62
  10. 2023Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMscited by 62
  11. 2019Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphscited by 59
  12. 2022TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Basescited by 59
  13. 2024M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitionscited by 38
  14. 2022Enhancing Multi-modal and Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generationcited by 28
  15. 2022COSPLAY: Concept Set Guided Personalized Dialogue Generation Across Both Party Personascited by 20
  16. 2024LLM-Personalize: Aligning LLM Planners with Human Preferences via Reinforced Self-Training for Housekeeping Robotscited by 18
  17. 2023keqing: knowledge-based question answering is a nature chain-of-thought mentor of LLMcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 13; 2026: 24.

38 papers.

Sort:

By area:

  1. 2025Memory in the Age of AI Agentscited by 285
  2. 2025PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memorycited by 82
  3. 2025A Survey on the Optimization of Large Language Model-based Agentscited by 45
  4. 2025Large Language Models for Planning: A Comprehensive and Systematic Surveycited by 38
  5. 2025Synergizing RAG and Reasoning: A Systematic Reviewcited by 27
  6. 2025A Survey of Personalization: From RAG to Agentcited by 26
  7. 2025AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systemscited by 23
  8. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applicationscited by 22
  9. 2026OP-Bench: Benchmarking Over-Personalization for Memory-Augmented Personalized Conversational Agentscited by 18
  10. 2025MMPB: It's Time for Multi-Modal Personalizationcited by 14
  11. 2025Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interactioncited by 11
  12. 2025AssoMem: Scalable Memory QA with Multi-Signal Associative Retrievalcited by 10
26 more
  1. 2026AIBuildAI: An AI Agent for Automatically Building AI Modelscited by 10
  2. 2026MemSyco-Bench: Benchmarking Sycophancy in Agent Memorycited by 9
  3. 2025ID-RAG: Identity Retrieval-Augmented Generation for Long-Horizon Persona Coherence in Generative Agentscited by 7
  4. 2026How Does Personalized Memory Shape LLM Behavior? Benchmarking Rational Preference Utilization in Personalized Assistantscited by 7
  5. 2024CARROT: A Learned Cost-Constrained Retrieval Optimization System for RAGcited by 5
  6. 2025The Personalization Trap: How User Memory Alters Emotional Reasoning in LLMscited by 5
  7. 2026PSPA-Bench: A Personalized Benchmark for Smartphone GUI Agentcited by 4
  8. 2026HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolutioncited by 4
  9. 2026Mem-π: Adaptive Memory through Learning When and What to Generatecited by 3
  10. 2026Know You Before You Speak: User-State Modeling for LLM Personalization in Multi-Turn Conversationcited by 3
  11. 2025Do Retrieval-Augmented Language Models Adapt to Varying User Needs?cited by 2
  12. 2026MOSAIC: Unveiling the Moral, Social and Individual Dimensions of Large Language Modelscited by 2
  13. 2026HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialoguescited by 2
  14. 2026IntrAgent: An LLM Agent for Content-Grounded Information Retrieval through Literature Reviewcited by 2
  15. 2026AdaMem: Learning What to Remember with Adaptive Memory Policies for Personalized Agentscited by 2
  16. 2026HippoCamp: Benchmarking Contextual Agents on Personal Computerscited by 1
  17. 2026Opal: Private Memory for Personal AIcited by 1
  18. 2026StratMem-Bench: Evaluating Strategic Memory Use in Virtual Character Conversation Beyond Factual Recallcited by 1
  19. 2026From Volume to Value: Preference-Aligned Memory Construction for On-Device RAGcited by 1
  20. 2026HUSH-Bench: Measuring Memory-Use Boundaries for Sensitive History in Conversational Agentscited by 1
  21. 2026Bridge-RAG: An Abstract Bridge Tree Based Retrieval Augmented Generation Algorithmcited by 0
  22. 2026From Empathy to Personalized Empathy: Adapting Empathetic Strategies to Individual Userscited by 0
  23. 2026Learning to Adapt Cross-Domain Preferences via Meta-LoRA for LLM Personalizationcited by 0
  24. 2026Graph-Based Personalized Memory for LLM Agents: Representation, Evolution, Retrieval, and Evaluationcited by 0
  25. 2026Learning from Others, Acting for You: Cross-User Memory Sharing for LLM Agentscited by 0
  26. 2026Privacy in Personalized AI Is a System Property, Not Just a Model Propertycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Enabling Personalized Long-term Interactions in LLM-based Agents through Persistent Memory and User Profiles
  2. 2026Me-Agent: A Personalized Mobile Agent with Two-Level User Habit Learning for Enhanced Interaction
  3. 2026HGP:An on-device personalized agent memory via hybrid graph storage
  4. 2025C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation
  5. 2025MobileRAG: Enhancing Mobile Agent with Retrieval-Augmented Generation
  6. 2026MobileMem: Learning from a Year of Mobile Experiences
  7. 2026APeB: Benchmarking Personalization Ability of Large Language Model Agents
  8. 2025PersonaAgent: Bridging Memory and Action for Personalized LLM Agents