用时间顺序组织对话记忆，提升长程对话智能体表现
Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents
- 构建按时间顺序排列的分段树记忆结构，逐条插入新对话
- 在三个基准上优于扁平/图/树形记忆，提升回答准确率
- 强调时间顺序对智能体记忆至关重要，适合长期交互场景
长程对话智能体需处理随时间演进的事件、任务与目标。现有记忆系统多按主题相似性组织，常忽略事件发生顺序。本文提出分段树记忆（SegTreeMem），将对话历史表示为基于话语的时间有序分段树。通过在线右端前沿更新规则，增量式插入新话语，保持时间顺序的同时形成层级记忆片段。检索时，通过树结构传播相关性得分，融合局部语义匹配与层级时间上下文。在三个长程记忆基准和两种大模型架构下，SegTreeMem均显著优于扁平检索、图结构记忆和树结构记忆基线。额外的时间顺序扰动实验表明，性能提升依赖于记忆构建中保留时间顺序，验证了时间顺序是智能体记忆的关键结构。
原文摘要 · Abstract (English)
Long-horizon conversational agents need to interact with users through evolving events, tasks, and goals. Such histories are naturally temporal, yet many existing memory systems organize information primarily by topical similarity and may ignore the order in which events occur. We introduce Segment Tree Memory, or SegTreeMem, a memory architecture that represents conversation history as a temporally ordered Segment Tree over utterances. SegTreeMem incrementally inserts new utterances through an online rightmost-frontier update rule, preserving chronological order while forming hierarchical memory segments. For retrieval, SegTreeMem propagates relevance scores through the tree to combine local semantic matching with hierarchical temporal context. Across three long-horizon memory benchmarks and two LLM backbones, SegTreeMem improves answer quality over flat retrieval, graph-structured memory, and tree-structured memory baselines. Additional temporal-order permutation analysis shows that the performance gain depends on preserving temporal order during memory construction, supporting the claim that temporal order is a key structure for agentic memory.
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。