Memory enables Large Language Model (LLM) agents to perceive, store, and use information from past dialogues, which is essential for personalization. However, existing methods fail to properly model the temporal dimension of memory in two aspects: 1) Temporal inaccuracy: memories are organized by dialogue time rather than their actual occurrence time; 2) Temporal fragmentation: existing methods focus on point-wise memory, losing durative information that captures persistent states and evolving patterns. To address these limitations, we propose Temporal Semantic Memory (TSM), a memory framework that models semantic time for point-wise memory and supports the construction and utilization of durative memory. During memory construction, it first builds a semantic timeline rather than a dialogue one. Then, it consolidates temporally continuous and semantically related information into a durative memory. During memory utilization, it incorporates the query's temporal intent on the semantic timeline, enabling the retrieval of temporally appropriate durative memories and providing time-valid, duration-consistent context to support response generation. Experiments on LongMemEval and LoCoMo show that TSM consistently outperforms existing methods and achieves up to 12.2% absolute improvement in accuracy, demonstrating the effectiveness of the proposed method.

翻译：记忆使大型语言模型（LLM）代理能够感知、存储和利用历史对话信息，这对实现个性化至关重要。然而，现有方法在记忆的时间维度建模上存在两方面不足：1）时序不准确性：记忆按对话时间而非实际发生时间组织；2）时序碎片化：现有方法侧重于点状记忆，丢失了捕捉持续状态与演化模式的持续性信息。为突破这些局限，我们提出时序语义记忆（TSM）——一种为点状记忆建模语义时间并支持持续性记忆构建与利用的记忆框架。在记忆构建阶段，TSM首先建立语义时间线而非对话时间线，进而将时间连续且语义相关的信息整合为持续性记忆。在记忆利用阶段，框架结合查询在语义时间线上的时序意图，实现时序适配的持续性记忆检索，并提供时间有效、持续一致的上下文以支持响应生成。在LongMemEval与LoCoMo数据集上的实验表明，TSM持续优于现有方法，准确率最高提升12.2%，验证了所提方法的有效性。