用事件分割理论构建对话记忆，让长期对话更连贯。
ES-Mem: Event Segmentation-Based Memory for Long-Term Dialogue Agents
- 基于事件分割理论动态划分对话片段，保持语义完整。
- 分层记忆架构结合边界语义，实现精准上下文定位。
- 适合需要长期记忆与连贯性的智能对话系统。
记忆对对话代理在长期互动中维持连贯性与持续适应至关重要。现有记忆机制虽具备基础存储与检索能力，但仍面临两大局限：(1) 固定的记忆粒度常破坏语义完整性，导致记忆单元碎片化、不连贯；(2) 普遍采用的扁平检索范式仅依赖表面语义相似性，忽视话语结构线索，难以精确定位特定叙事上下文。为此，受事件分割理论启发，我们提出ES-Mem框架，包含两个核心组件：(1) 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) 分层记忆架构，构建多层级记忆，并利用边界语义锚定特定情节记忆，实现精确上下文定位。在两个记忆基准上的评估显示，ES-Mem相较于基线方法始终取得性能提升。此外，所提出的事件分割模块在对话分割数据集上也展现出良好的泛化能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。