Abstract
AI agents that interact with users across multiple sessions require persistent long-term memory to maintain coherent, personalized behavior. Current approaches either rely on flat retrieval-augmented generation (RAG), which loses structural relationships between memories, or use memory compression and vector retrieval that cannot capture the associative structure of multi-session conversations. There are few graph based techniques proposed in the literature, however they still suffer from hub dominated retrieval and poor hierarchical reasoning over evolving memory. We propose GAAMA, a graph-augmented associative memory system that constructs a concept-mediated hierarchical knowledge graph through a three-step pipeline: (1)~verbatim episode preservation from raw conversations, (2)~LLM-based extraction of atomic facts and topic-level concept nodes, and (3)~synthesis of higher-order reflections. The resulting graph uses four node types (episode, fact, reflection, concept) connected by five structural edge types, with concept nodes providing cross-cutting traversal paths that complement semantic similarity. Retrieval combines cosine-similarity-based $k$-nearest neighbor search with edge-type-aware Personalized PageRank (PPR) through an additive scoring function. On the LoCoMo-10 benchmark (1,540 questions across 10 multi-session conversations), GAAMA achieves 78.9\% mean reward, outperforming a tuned RAG baseline (75.0\%), HippoRAG (69.9\%), A-Mem (47.2\%), and Nemori (52.1\%). Ablation analysis shows that augmenting graph-traversal-based ranking (Personalized PageRank) with semantic search consistently improves over pure semantic search on graph nodes (+1.0 percentage point overall).
Abstract (translated)
在多轮会话中与用户交互的AI代理需要持久的长期记忆来维持连贯且个性化的行为。当前方法要么依赖扁平化的检索增强生成（RAG），该方法会丢失记忆间的结构关系；要么使用记忆压缩和向量检索，无法捕捉多轮会话对话中的联想结构。文献中虽提出了一些基于图的技术，但仍受限于中心节点主导的检索以及对动态演化记忆的层次化推理能力不足。我们提出GAAMA，一个图增强联想记忆系统，它通过三步流水线构建概念介导的层次化知识图谱：(1) 从原始对话中逐字保留情景片段，(2) 基于大语言模型提取原子事实和主题级概念节点，(3) 合成高阶反思。生成的图谱包含四种节点类型（情景片段、事实、反思、概念），通过五种结构边类型连接，其中概念节点提供跨主题的遍历路径，以补充语义相似性。检索通过加性评分函数，将基于余弦相似度的k近邻搜索与考虑边类型感知的个性化PageRank（PPR）相结合。在LoCoMo-10基准测试（涵盖10轮多会话对话的1540个问题）中，GAAMA达到78.9%的平均奖励，优于调优后的RAG基线（75.0%）、HippoRAG（69.9%）、A-Mem（47.2%）和Nemori（52.1%）。消融分析表明，在语义搜索基础上增加基于图遍历的排序（个性化PageRank）始终优于仅对图谱节点进行纯语义搜索（整体提升1.0个百分点）。
URL
https://arxiv.org/abs/2603.27910
