# TRACE: State-Aware Query Processing over Temporal Evidence Graphs for Conversational Data Source: [TRACE: State-Aware Query Processing over Temporal Evidence Graphs for Conversational Data]() Collection index: [llms.txt]() Data updated: 2026-07-03T05:00:04.967Z Authors: Maolin Wang, Yu Wang, Zichun Liu, Baiyuan Qiu, Chenbin Zhang, Jiguang Shen, Haoran Yang, Hao Miao Published: 2026-07-01T02:28:47.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Long-context Question Answering on LoCoMo (test)](): Long-context Question Answering; LoCoMo (test); LLM Score (Temporal): 72.3. - [Memory-augmented generation on LongMemEvalS (test)](): Memory-augmented generation; LongMemEvalS (test); User LLM (Single-Session): 93.8. ## Original sources and implementation [Original paper]() [PDF]()