Human-agent dialogues often exhibit topic continuity-a stable thematic frame that evolves through temporally adjacent exchanges-yet most large language model (LLM) agent memory systems fail to preserve it. Existing designs follow a fragmentation-compensation paradigm: they first break dialogue streams into isolated utterances for storage, then attempt to restore coherence via embedding-based retrieval. This process irreversibly damages narrative and causal flow, while biasing retrieval towards lexical similarity. We introduce membox, a hierarchical memory architecture centered on a Topic Loom that continuously monitors dialogue in a sliding-window fashion, grouping consecutive same-topic turns into coherent "memory boxes" at storage time. Sealed boxes are then linked by a Trace Weaver into long-range event-timeline traces, recovering macro-topic recurrences across discontinuities. Experiments on LoCoMo demonstrate that Membox achieves up to 68% F1 improvement on temporal reasoning tasks, outperforming competitive baselines (e.g., Mem0, A-MEM). Notably, Membox attains these gains while using only a fraction of the context tokens required by existing methods, highlighting a superior balance between efficiency and effectiveness. By explicitly modeling topic continuity, Membox offers a cognitively motivated mechanism for enhancing both coherence and efficiency in LLM agents.

翻译：人机对话常呈现主题连续性——一种通过时间相邻的对话轮次演化的稳定主题框架——然而大多数大语言模型（LLM）智能体记忆系统未能有效保持这一特性。现有设计遵循“碎片化-补偿”范式：先将对话流拆解为孤立语句进行存储，再尝试通过基于嵌入的检索恢复连贯性。这一过程不可逆地破坏了叙事与因果流，并使检索偏向于词汇相似性。我们提出membox，一种以“主题织机”为核心的分层记忆架构，该组件以滑动窗口方式持续监控对话，在存储时将连续同主题的对话轮次组织为连贯的“记忆盒”。封装后的记忆盒通过“轨迹编织器”连接为长程事件时间线轨迹，从而恢复跨越间断的宏观主题复现。在LoCoMo数据集上的实验表明，Membox在时序推理任务上实现了最高68%的F1值提升，优于现有基线方法（如Mem0、A-MEM）。值得注意的是，Membox仅需消耗现有方法所需上下文词元的一小部分即可达成上述性能，彰显了其在效率与效能间的优越平衡。通过显式建模主题连续性，Membox提供了一种符合认知机理的机制，可同时增强LLM智能体的连贯性与运行效率。