发表机构
Korea University; Boston University（高丽大学; 波士顿大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对现有对话智能体记忆系统的角色与事件松散耦合问题，提出PGMem异构角色记忆图，通过溯源边关联角色与事件，在多个基准测试中性能优于多种基线方法。
AI 中文摘要
长期个性化对话智能体需跟踪用户偏好随角色的演变。现有记忆系统能很好地组织过往事件，但将角色存储为与支撑它们的事件分离的扁平轮廓，这种松散耦合导致记忆-角色有效性差距和角色感知检索差距。我们提出PGMem，一种异构角色记忆图，通过类型化溯源和证据边连接事件节点与角色节点，使每个角色信号可追溯到支持或修改它的事件。检索时，PGMem从查询相关种子扩展，按证据有效性对信号排序。在三个采用小语言模型骨干的基准测试中，PGMem始终优于基于摘要、角色感知、图结构和智能体记忆基线，且随上下文增长性能提升。PGMem的源代码可在该https URL获取。
英文摘要
Long-term personalized dialogue agents must track user preferences as their personas evolve. Existing memory systems organize past events well, but store personas as flat profiles detached from the events that justify them. This loose coupling leads to the memory-persona validity gap and the persona-aware retrieval gap. We propose PGMem, a heterogeneous persona-memory graph that connects event and persona nodes through typed provenance and evidence edges, keeping each persona signal traceable to the events that support or revise it. At retrieval time, PGMem expands from query-relevant seeds and ranks signals by evidential validity. Across three benchmarks with small language model backbones, PGMem consistently outperforms summary-based, persona-aware, graph-structured, and agentic memory baselines, and improves performance as the context grows. The source code of PGMem is available at https://github.com/wonjunchoi23/pgmem/
CommentsEMNLP 2026 (main)
