让AI伴侣记住用户偏好与情感变化，提升长期陪伴感。
ZifaMem: Structured Memory for Persona, Preference, and Emotional Continuity in AI Companions
- 用结构化记忆分层存储对话摘要、事件记忆和用户模型。
- 情感智能得分提升11.4%，角色一致性改善超42%。
- 适合开发有持续人格的AI助手或社交机器人。
AI伴侣不仅需单轮对话流畅，更需维持情感连续性：记住自身身份、用户偏好及关系演变。我们提出ZifaMem，一种将对话分为会话摘要、情景记忆和整合用户模型的结构化记忆系统。在固定大模型评分协议与路径审计下，相比直接使用原始对话历史的基准，结构化记忆使四类骨干模型的情感智能综合得分提升11.4%（95%置信区间6.3%至17.1%），角色定位准确率在所有四个骨干模型上均显著提高（如Claude模型提升42%）。多轮情绪上下文相较单轮快照，偏好度提升39%（探索性结果）；而额外引入情绪状态机未在五个评估指标中带来可测量提升。在相同预注册协议下，三种记忆系统（ZifaMem、Mem0、过滤式原文检索）均显著优于原始历史部署，且ZifaMem与Mem0在预注册主偏好指标上差异小于±5分，统计等效。ZifaMem SDK、CLI及可移植代理技能已开源：https://github.com/zifacorp/zifamem。
原文摘要 · Abstract (English)
AI companions are judged not only by single-turn fluency but by whether they sustain emotional continuity: remembering who the companion is, what the user prefers, and how the relationship has felt. We present ZifaMem, a structured memory system that organizes dialogue into session summaries, episodic memories, and a consolidated user model. Against a deployment-honest comparator that supplies the full raw dialogue history, and under a fixed LLM-as-a-judge protocol with route audits, structured memory raises pooled four-backbone emotional-intelligence scores by 11.4% (95% CI 6.3% to 17.1%), and persona grounding improves on all four backbones (Claude +42% relative). Multi-turn affect context wins a +39% net preference over a single-turn snapshot (exploratory), whereas an additional emotion state machine yields no measurable gain on any of five endpoints. Under an identical preregistered protocol, three memory systems (ZifaMem, Mem0, and filtered verbatim retrieval) each improve significantly over raw-history deployment, and ZifaMem and Mem0 are statistically equivalent within +/-5 points on the preregistered primary preference endpoint. The ZifaMem SDK, CLI, and portable Agent Skills are open-sourced at https://github.com/zifacorp/zifamem.
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。