arXiv cs.CL· Yichen Liu, Chunfeng Yuan, Haowei Liu, Wenjuan Li, Zefeng Lin, Bing Li, Xu Chen, Weiming Hu·· 9 天前AI 评分25
QGMem：面向长期对话智能体的事件中心记忆与查询感知图增强框架
Event-Centric Memory with Query-Aware Graph Augmentation for Long-Term Conversational Agents
AI 导读
针对现有扁平化记忆隐式丢失事件关系、图记忆构建成本高且引入无关关系的问题，研究者提出 QGMem 记忆构建与激活框架，将长对话历史转为事件索引的原子记忆单元并整合为动态记忆痕迹。
正文 · 原文
Abstract:For persistent and personalized conversational agents, memory systems can enable them to remember, update, and reason over long histories by storing past interactions and retrieving relevant information. Existing memory systems typically follow two paradigms: flat-structured memory and graph-based memory. The former is lightweight but leaves event relations and state updates implicit, while the latter explicitly models memory structure but incurs additional construction cost and introduces irrelevant relations over long histories. To address these limitations, we propose QGMem, a novel memory construction and activation framework motivated by human memory, in which experience is organized into events and query-relevant events are modeled by graph as working memory. QGMem converts long dialogue histories into event-indexed atomic memory units that preserve individual experiences and consolidates related units into dynamic memory traces that retain state trajectories and current states. When a query arrives, hybrid memory retrieval gathers complementary candidate memories, and query-aware reranking activates the most relevant units as a compact working memory. To expose relational dependencies in the working memory and support conflict-aware reasoning, QGMem organizes the working memory as a local graph, which is then encoded as a graph token and provided to the LLM together with the textual working memory to improve evidence utilization during answer generation. Experiments across six benchmarks validate the framework and show consistent gains in retrieval, multi-hop evidence composition, conflict resolution, and ultra-long dialogue reasoning with compact contexts and moderate inference cost.
| Comments: | 17 pages, 7 figures. Submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.11920 [cs.CL] |
| (or arXiv:2610.11920v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11920 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yichen Liu [view email]
[v1]
Thu, 8 Oct 2026 13:17:59 UTC (505 KB)
来源：arXiv cs.CL · arxiv.org