个人人工智能：面向个性化LLM智能体的知识图谱存储与检索方法的系统性比较

摘要

如何通过有效整合用户交互历史实现语言模型个性化，仍是开发自适应人工智能系统的核心挑战。尽管基于检索增强生成（RAG）技术的大型语言模型（LLM）提升了事实准确性，但它们往往缺乏结构化记忆机制，难以适应复杂长期交互场景。为此，我们提出一种基于知识图谱的灵活外部记忆框架，该图谱由LLM自动构建并动态更新。在AriGraph架构基础上，我们创新性地引入支持标准边与两种超边类型的混合图结构，从而实现丰富且动态的语义与时序表征。该框架还支持A*算法、WaterCircles遍历、束搜索及混合方法等多重检索机制，使其能适配不同数据集与LLM能力。我们在TriviaQA、HotpotQA和DiaASQ基准测试上的实验表明，不同记忆与检索配置可针对特定任务实现最优性能。此外，我们为DiaASQ基准扩展了时序标注和内部矛盾陈述，证明本系统在处理时序依赖与情境感知推理时仍保持鲁棒性与有效性。

English

Personalizing language models by effectively incorporating user interaction history remains a central challenge in the development of adaptive AI systems. While large language models (LLMs), combined with Retrieval-Augmented Generation (RAG), have improved factual accuracy, they often lack structured memory and fail to scale in complex, long-term interactions. To address this, we propose a flexible external memory framework based on a knowledge graph that is constructed and updated automatically by the LLM. Building upon the AriGraph architecture, we introduce a novel hybrid graph design that supports both standard edges and two types of hyper-edges, enabling rich and dynamic semantic and temporal representations. Our framework also supports diverse retrieval mechanisms, including A*, WaterCircles traversal, beam search, and hybrid methods, making it adaptable to different datasets and LLM capacities. We evaluate our system on TriviaQA, HotpotQA, DiaASQ benchmarks and demonstrate that different memory and retrieval configurations yield optimal performance depending on the task. Additionally, we extend the DiaASQ benchmark with temporal annotations and internally contradictory statements, showing that our system remains robust and effective in managing temporal dependencies and context-aware reasoning

个人人工智能：面向个性化LLM智能体的知识图谱存储与检索方法的系统性比较

PersonalAI: A Systematic Comparison of Knowledge Graph Storage and Retrieval Approaches for Personalized LLM agents

摘要

Support