发表机构
National University of Defense Technology（国防科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
AutoViewMem通过自配置低重叠语义视图在写入时解缠对话记忆，无需显式路由，在LoCoMo和PersonaMem基准上显著提升长时程问答与个性化性能。
AI 中文摘要
长期记忆对于大型语言模型（LLM）智能体在长时间交互中保持一致性和个性化至关重要。现有的记忆系统通常依赖固定的粒度或静态模式，但当异构信息（如偏好、事件、约束和时间更新）嵌入到单一的混合表示中时，这些设计会面临困难。由此产生的语义干扰使得top-K检索对噪声敏感，并常常导致相关证据排名不佳。我们提出了AutoViewMem，一种数据驱动的框架，在索引之前将长期对话记忆组织成自配置、低重叠的语义视图。AutoViewMem从交互轨迹中发现候选视图，选择一组紧凑的互补视图，并利用这些视图在写入时指导基于来源的结构化记忆提取。这种表示优先的设计将语义解缠从检索时间转移到写入时间，使得标准的top-K相似性搜索能够检索到聚焦的证据，而无需显式路由或迭代检索。我们进一步应用离线整合来提高记忆的紧凑性和一致性。在LoCoMo和PersonaMem基准上，在Qwen3-8B和Qwen3-14B骨干模型下进行的实验表明，AutoViewMem在保持简单推理流程的同时，在长时程问答和个性化方面优于强大的记忆基线。
英文摘要
Long-term memory is essential for large language model (LLM) agents to maintain consistency and personalization over extended interactions. Existing memory systems typically rely on fixed granularities or static schemas, but these designs struggle when heterogeneous information, such as preferences, events, constraints, and temporal updates, is embedded in a single mixed representation. The resulting semantic interference makes top-K retrieval sensitive to noise and often leaves relevant evidence poorly ranked. We present AutoViewMem, a data-driven framework that organizes long-term conversational memory into self-configuring, low-overlap semantic views before indexing. AutoViewMem discovers candidate views from interaction traces, selects a compact complementary view set, and uses these views to guide write-time structured extraction of provenance-grounded memories. This representation-first design moves semantic disentanglement from retrieval time to write time, allowing standard top-K similarity search to retrieve focused evidence without explicit routing or iterative retrieval. We further apply offline consolidation to improve memory compactness and consistency. Experiments on the LoCoMo and PersonaMem benchmarks, under both Qwen3-8B and Qwen3-14B backbones, show that AutoViewMem improves long-horizon question answering and personalization over strong memory baselines while preserving a simple inference pipeline.
