Memory is critical for dialogue agents to maintain coherence and enable continuous adaptation in long-term interactions. While existing memory mechanisms offer basic storage and retrieval capabilities, they are hindered by two primary limitations: (1) rigid memory granularity often disrupts semantic integrity, resulting in fragmented and incoherent memory units; (2) prevalent flat retrieval paradigms rely solely on surface-level semantic similarity, neglecting the structural cues of discourse required to navigate and locate specific episodic contexts. To mitigate these limitations, drawing inspiration from Event Segmentation Theory, we propose ES-Mem, a framework incorporating two core components: (1) a dynamic event segmentation module that partitions long-term interactions into semantically coherent events with distinct boundaries; (2) a hierarchical memory architecture that constructs multi-layered memories and leverages boundary semantics to anchor specific episodic memory for precise context localization. Evaluations on two memory benchmarks demonstrate that ES-Mem yields consistent performance gains over baseline methods. Furthermore, the proposed event segmentation module exhibits robust applicability on dialogue segmentation datasets.

翻译：记忆对于对话智能体在长期交互中保持连贯性和实现持续适应至关重要。尽管现有的记忆机制提供了基础的存储与检索能力，但它们受到两个主要局限的制约：(1) 僵化的记忆粒度常常破坏语义完整性，导致记忆单元碎片化且不连贯；(2) 普遍采用的扁平化检索范式仅依赖于表层语义相似性，忽视了导航和定位特定情景语境所需的话语结构线索。为缓解这些局限，受事件分割理论启发，我们提出了ES-Mem框架，该框架包含两个核心组件：(1) 一个动态事件分割模块，将长期交互划分为具有明确边界的语义连贯事件；(2) 一个分层记忆架构，构建多层记忆并利用边界语义来锚定特定情景记忆，以实现精确的语境定位。在两个记忆基准测试上的评估表明，ES-Mem相较于基线方法取得了持续的性能提升。此外，所提出的事件分割模块在对话分割数据集上展现出良好的适用性。