发表机构
INSAIT, Sofia University “St. Kliment Ohridski”; Newcastle University; Linköping University（INSAIT，索非亚大学“圣克莱门特·奥赫里德斯基”分校; 纽卡斯尔大学; 林雪平大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对现有方法不足，提出AI YOU框架，结合多种技术进行角色推断，通过记忆机制保持一致性，实验显示其在共形覆盖、不确定性校准等方面表现良好，提升了角色保真度，AI YOU Town原型可用于未来交互。
AI 中文摘要
现有推断用户特征并生成符合角色回应的方法依赖静态提示，存在缺乏校准不确定性、忽视序列证据及长时间交互中漂移等问题。我们提出了AI YOU框架，它通过对话不断更新22维的个性档案，并体现在个人数字分身中。该系统结合提示、贝叶斯更新和共形预测进行角色推断，通过定期刷新的记忆锚点和三层认知记忆保持长期交互中的角色一致性。实验结果表明，AI YOU实现了0.921至0.976的共形覆盖，改善了不确定性校准和基于记忆的推理，在对抗设置下提升了角色保真度并减少了特征漂移。AI YOU Town原型为未来交互初始化了一个虚拟双世界，在线演示可通过链接获取。
英文摘要
Existing approaches to infer user traits and generate responses consistent with a persona rely on static prompting. They lack calibrated uncertainty, ignore sequential evidence, and drift during long interactions. We present \textbf{AI YOU}, a framework that continually updates a personality profile with 22 dimensions from conversation and embodies it in a personal digital twin. Practically, the system combines prompting, Bayesian updating, and conformal prediction for persona inference. A periodically refreshed memory anchor and cognitive memory with three layers preserve persona consistency over long interactions. Across the main results, AI YOU \emph{(i)} achieves conformal coverage ranging from 0.921 to 0.976, \emph{(ii)} improves uncertainty calibration and reasoning grounded in memory, and \emph{(iii)} enhances persona fidelity over static prompting in role playing over 100 turns while reducing trait drift, for most evaluated backbones under adversarial settings with multiple agents. The prototype \emph{AI YOU Town} initializes an imaginative twin world for future interaction. The online demo is available at \href{https://quinnnnnne-ai-you.hf.space/}{\mbox{\texttt{quinnnnnne-ai-you.hf.space}}}.
Comments28 pages
