QUMem：面向大语言模型智能体查询条件用户状态推理的个性化记忆
QUMem: Personalized Memory for Query-Conditioned User-State Inference in LLM Agents
浏览论文内容
中文总结 AI 辅助
QUMem 是一种结构化记忆框架，通过分割交互历史、分解记忆类型、多查询检索等方法，在 PersonaMem 和 KnowU-Bench 上实现了查询条件用户状态推理的最优性能，提升了大语言模型智能体的长期个性化能力。
中文摘要 AI 辅助
大语言模型（LLM）智能体越来越多地利用外部记忆系统，通过调用漫长且不断演变的交互历史来支持个性化，而用户偏好在这些历史中可能随时间分布、随情境变化，且与早期证据存在冲突。然而，现有系统面临三个局限：固定轮次、固定令牌或基于会话的边界会将不相关对话混合，或将事件与其原因、决策和结果拆分；将同一交互中的多条用户信息存储为单个记忆，会将具有不同功能、应独立检索的条目绑定在一起；将当前任务视为单个 top-k 检索查询，会返回单独相关但无法共同捕捉偏好演变、时间有效性和情境适用性的片段。我们推出 QUMem，这是一种用于查询条件用户状态推理的结构化记忆框架。QUMem 首先根据语义连续性将交互历史分割为可变长度的片段，然后将每个片段分解为可独立检索的事实、偏好和可迁移见解记忆，同时保留时间位置和来源证据。在推理时，三个顺序智能体分别识别任务特定的信息需求、规划对类型化记忆存储的多查询检索，并共同推断出时间和情境上有效的用户状态，以用于下游响应生成。QUMem 在 PersonaMem 和 KnowU-Bench 上均取得了最先进的性能，证明了面向长期个性化的查询条件用户状态推理的有效性。
英文摘要
Large language model (LLM) agents increasingly use external memory systems to support personalization by drawing on long and evolving interaction histories, in which user preferences may be distributed across time, change with context, and conflict with earlier evidence. However, existing systems face three limitations: fixed-turn, fixed-token, or session-based boundaries can mix unrelated dialogue or split an event from its causes, decisions, and outcomes; storing multiple pieces of user information from the same interaction as a single memory binds together items that serve different functions and should be independently retrievable; and treating the current task as a single top-$k$ retrieval query can return fragments that are individually relevant but fail to jointly capture preference evolution, temporal validity, and contextual applicability. We introduce \textsc{QUMem}, a structured memory framework for query-conditioned user-state inference. \textsc{QUMem} first segments interaction histories into variable-length episodes according to semantic continuity, then decomposes each episode into independently retrievable factual, preference, and transferable insight memories while preserving temporal positions and source evidence. At inference time, three sequential agents identify task-specific information needs, plan multi-query retrieval over the typed memory stores, and jointly infer a temporally and contextually valid user state for downstream response generation. \textsc{QUMem} achieves state-of-the-art performance on both PersonaMem and KnowU-Bench, demonstrating the effectiveness of query-conditioned user-state inference for long-term personalization.
