发表机构
Tencent Youtu Lab; Zhejiang Key Laboratory of Industrial Intelligence and Digital Twin, EIT, Ningbo, China; Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China; Shenzhen Loop Area Institute, Shenzhen, China（腾讯优图实验室; 浙江省工业智能与数字孪生重点实验室; 香港理工大学计算学系; 深圳市环区研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出LGM神经符号框架，通过潜在图构建与稀疏自编码器解缠长期记忆，实现查询感知的个性化推理，在基准上显著超越现有方法。
AI 中文摘要
个性化智能体需要基于长期历史交互进行推理，以推断显性偏好和隐性行为证据。早期的平面检索方法独立地对记忆片段进行评分，忽视了分布式信息，而当前的结构化记忆框架依赖于与查询无关的静态图，无法捕捉依赖于上下文的关联。关键在于，原始文本记忆本质上是纠缠且嘈杂的，使得细粒度个性化和跨会话推理在计算上变得不可行。为此，我们提出了LGM，一种新颖的神经符号框架，将长期记忆解缠转移到连续潜在空间中。具体而言，(i) 我们不持久化固定图，而是设计了一种带有稀疏自编码器的定制潜在图构建方法。针对每个查询，它将历史交互映射到潜在记忆节点，并将记忆痕迹解缠为稀疏概念激活，动态合成查询感知的关系边权重。(ii) 随后，图编码器将查询嵌入视为条件偏好，以指导跨任务特定潜在子图的非线性消息传递。这产生了高度表达性的记忆表示，用于有效的激活。在长期个性化基准上的大量实验表明，LGM在捕捉显性和隐性偏好方面显著优于最先进的基线，同时能够实现个性化响应。
英文摘要
Personalized agents are required to reason over long-term history interactions to infer both explicit preferences and implicit behavioral evidence. While early flat retrieval methods score memory fragments independently and neglect the distributed information, current structured memory frameworks rely on query-agnostic static graphs that fail to capture the context-dependent relations. Crucially, raw textual memories are inherently entangled and noisy, making fine-grained personalization and cross-session reasoning computationally prohibitive. To this end, we present LGM, a novel neuro-symbolic framework that shifts long-term memory disentanglement into a continuous latent space. Specifically, (i) instead of persisting fixed graphs, we design a tailored latent graph construction with a sparse autoencoder. Subject to each query, it maps historical interactions into latent memory nodes and disentangles the memory traces into sparse concept activations, dynamically synthesizing query-aware relational edge weights. (ii) A graph encoder then treats the query embedding as a conditioning preference to direct non-linear message passing across the task-specific latent subgraph. This yields a highly expressive memory representation for effective activations. Extensive experiments on long-term personalization benchmarks demonstrate that LGM significantly outperforms state-of-the-art baselines in capturing both explicit and implicit preferences while enabling personalized responses.
