用可编辑的记忆图增强大模型，打造个性化手机助手
Crafting Personalized Agents through Retrieval-Augmented Generation on Editable Memory Graphs
- 构建可编辑记忆图，结合检索生成技术
- 在真实数据集上提升10%性能，优于现有方法
- 适合开发智能手机个人助理的工程师
在移动互联网时代，用户数据（常被称为记忆）持续在个人设备上生成。如何有效管理并利用这些数据以提供个性化服务，是当前重要研究方向。本文提出一种基于大语言模型（LLMs）的个性化智能体构建新任务，通过调用用户手机中的记忆数据，增强下游应用的智能能力。为此，我们提出EMG-RAG方案，融合检索增强生成（RAG）与可编辑记忆图（EMG），并通过强化学习优化数据收集、可编辑性与选择性三大挑战。在真实世界数据集上的大量实验验证了该方法的有效性，在最佳现有方法基础上实现约10%的性能提升。此外，该个性化智能体已部署至实际智能手机AI助手，显著提升了用户体验。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。