发表机构
ZifaCorp; University of Science and Technology of China; Fudan University（紫发公司; 中国科学技术大学; 复旦大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对人工智能伴侣情感连续性问题，提出结构化记忆系统ZifaMem，通过组织对话形成多种记忆模型。实验表明其能提升情商得分、改善人物形象基础等，多种记忆系统均有改善，且ZifaMem与Mem0在主要偏好端点统计等效，相关工具已开源。
AI 中文摘要
人工智能伴侣不仅由单轮流畅性来评判，还取决于它们是否能保持情感连续性，即记住伴侣是谁、用户偏好什么以及关系感受如何。我们提出了ZifaMem，一种结构化记忆系统，它将对话组织成会话摘要、情景记忆和整合的用户模型。在与提供完整原始对话历史的部署诚实比较器对比时，在具有路由审核的固定大语言模型作为评判协议下，结构化记忆使四个主干的综合情商得分提高了11.4%（95%置信区间为6.3%至17.1%），人物形象基础在所有四个主干上都有改善。多轮情感上下文比单轮快照获得了39%的净偏好，而额外的情感状态机在五个端点上均未产生可测量的增益。在相同的预注册协议下，三种记忆系统（ZifaMem、Mem0和过滤逐字检索）均比原始历史部署有显著改善，且ZifaMem和Mem0在预注册的主要偏好端点上在正负5分范围内统计等效。ZifaMem的软件开发工具包、命令行界面和便携式智能体技能在该https网址开源。
英文摘要
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.
