超越对话时间：面向个性化LLM代理的时序语义记忆
Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents
AI总结：
本文提出TSM，一种面向个性化LLM代理的时序语义记忆框架，通过建模语义时间和持续记忆，提升对话任务的准确性和持续性。
摘要：
记忆使大型语言模型（LLM）代理能够感知、存储和使用过去对话中的信息，这对于个性化至关重要。然而，现有方法在两个方面未能正确建模记忆的时序维度：1）时间不准确：记忆按对话时间而非实际发生时间组织；2）时间碎片化：现有方法专注于点状记忆，丢失了捕捉持续状态和演变模式的持续信息。为了解决这些限制，我们提出了时序语义记忆（TSM），一种能够对点状记忆建模语义时间并支持构建和利用持续记忆的内存框架。在记忆构建过程中，它首先构建语义时间线而非对话时间线。然后，它将时间连续且语义相关的信息整合为持续记忆。在记忆利用过程中，它将查询的时序意图纳入语义时间线，使能够检索到合适的时间持续记忆，并提供时间有效的、持续一致的上下文以支持响应生成。在LongMemEval和LoCoMo上的实验表明，TSM在准确性上始终优于现有方法，并在准确率上达到最高12.2%的绝对提升，证明了所提方法的有效性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
