构建可追溯的个人记忆图谱，让对话代理随时间持续学习用户偏好。
PGMem: Tightly Coupled Persona-Memory Graph for Lifelong Personalized Agents
- 用事件与人格节点间的证据边，实现记忆与人格的紧密耦合。
- 在三个基准上优于基线模型，上下文越长效果越显著。
- 适合需要长期个性化交互的应用，如智能助手、虚拟陪伴。
长期个性化对话代理需跟踪用户偏好随时间演变。现有记忆系统虽能组织过往事件，但将人格信息存储为脱离事件支撑的扁平化档案，导致记忆-人格有效性差距与人格感知检索差距。我们提出PGMem，一种异构的人格-记忆图结构，通过类型化的来源与证据边连接事件与人格节点，确保每条人格信号均可追溯至支持或修正它的具体事件。检索时，PGMem从查询相关种子出发扩展，并根据证据有效性对信号进行排序。在三个采用小语言模型主干的基准测试中，PGMem持续优于基于摘要、人格感知、图结构及代理式记忆的基线模型，且随着上下文增长性能进一步提升。PGMem源代码已开源：https://github.com/wonjunchoi23/pgmem/
原文摘要 · Abstract (English)
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/
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。