Long-term conversational agents need memory systems that capture relationships between events, not merely isolated facts, to support temporal reasoning and multi-hop question answering. Current approaches face a fundamental trade-off: flat memory is efficient but fails to model relational structure, while graph-based memory enables structured reasoning at the cost of expensive and fragile construction. To address these issues, we propose \textbf{StructMem}, a structure-enriched hierarchical memory framework that preserves event-level bindings and induces cross-event connections. By temporally anchoring dual perspectives and performing periodic semantic consolidation, StructMem improves temporal reasoning and multi-hop performance on \texttt{LoCoMo}, while substantially reducing token usage, API calls, and runtime compared to prior memory systems, see https://github.com/zjunlp/LightMem .

翻译：长期对话智能体需要能够捕捉事件间关系的记忆系统，而非仅记录孤立事实，以支持时序推理与多跳问答。现有方法面临根本性权衡：平面记忆虽高效但无法建模关系结构，而基于图的记忆虽能实现结构化推理却构建成本高昂且脆弱。为解决这些问题，我们提出\textbf{StructMem}——一种结构增强的分层记忆框架，既可保留事件级绑定，又能诱发跨事件关联。通过时间锚定双重视角并执行周期性语义整合，StructMem在\texttt{LoCoMo}数据集上显著提升了时序推理与多跳问答性能，同时相较现有记忆系统大幅降低令牌消耗、API调用次数与运行时间（详见https://github.com/zjunlp/LightMem）。