TRACE：面向对话数据的时间证据图状态感知查询处理
TRACE: State-Aware Query Processing over Temporal Evidence Graphs for Conversational Data
AI总结：
提出TRACE框架，通过构建时间证据图并维护有效性标注，实现对话数据中状态感知的查询处理，提升时间推理和多跳推理能力。
摘要：
对话数据越来越多地被用作长期运行的助手和AI代理的持久用户状态来源。然而，查询这些数据仍然具有挑战性，因为对话自然演化：计划被修订，偏好发生变化，后续消息经常取代或矛盾早期信息。现有的长期记忆管道主要将记忆视为独立的文本或向量对象。这种方法通常检索语义相似但过时的证据，对状态感知推理的支持有限。为了解决这个问题，我们提出了TRACE，一个针对演化对话数据的时间证据图的查询处理框架。TRACE将对话建模为一个跨越事件、会话和主题的层次图，并丰富了类型化的时间、因果、更新和矛盾关系。关键的是，该框架维护有效性标注，使得过时事实对于历史查询仍然可访问，但在当前状态答案中被折扣。在查询时，TRACE结合了基于向量的笔记检索与图引导的证据搜索，生成有效性感知的支持路径和用于答案生成的混合上下文。这种设计将词汇检索与证据重建分离，使得在长对话历史上进行有界的查询时推理成为可能。在长对话问答（QA）基准上的实验表明，TRACE改进了时间和多跳推理，消融实验突出了层次结构、更新感知的种子和路径基础证据的重要性。
英文摘要：
Conversational data is increasingly used as a persistent source of user state for long-running assistants and AI agents. However, querying this data remains challenging because conversations naturally evolve: plans are revised, preferences change, and later messages frequently supersede or contradict earlier information. Existing long-memory pipelines largely treat memories as independent text or vector objects. This approach often retrieves semantically similar but stale evidence, offering limited support for state-aware reasoning. To address this problem, we present TRACE, a query processing framework over temporal evidence graphs for evolving conversational data. TRACE models conversations as a hierarchical graph spanning events, sessions, and topics, enriched with typed temporal, causal, update, and contradiction relations. Crucially, the framework maintains validity annotations so obsolete facts remain accessible for historical queries but are discounted for current-state answers. At query time, TRACE combines vector-based note retrieval with graph-guided evidence search, generating validity-aware support paths and a hybrid context for answer generation. This design separates lexical recall from evidence reconstruction, enabling bounded query-time reasoning over long conversational histories. Experiments on long-conversation query-answering (QA) benchmarks show that TRACE improves temporal and multi-hop reasoning, with ablations highlighting the importance of hierarchy, update-aware seeding, and path-grounded evidence.
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。
