用动态人格模型打造能长期保持一致的数字分身，对话更可信。
AI YOU Town: Make Friends and Money with Your Digital Twin
- 基于贝叶斯更新和置信预测，实时调整22维人格特征
- 100轮对话中减少性格漂移，置信覆盖率达92.1%~97.6%
- 适合想做持久角色扮演或社交互动的开发者与创作者
现有方法依赖静态提示推断用户特质并生成符合人设的回复，缺乏校准的不确定性估计，忽视序列证据，在长对话中易产生性格漂移。本文提出 extbf{AI YOU} 框架，通过对话持续更新22维人格画像，并以个人数字分身形式体现。系统结合提示工程、贝叶斯更新与共形预测实现人格推断；通过周期性刷新的记忆锚点与三层认知记忆结构，保障长期交互中的人格一致性。实验表明，AI YOU 在主要指标上表现优异： extit{(i)} 置信覆盖率达0.921至0.976； extit{(ii)} 显著提升不确定性校准能力与基于记忆的推理质量； extit{(iii)} 在多代理对抗环境下，相比静态提示，显著增强角色扮演中的人格保真度，减少特质漂移。原型系统 extit{AI YOU Town} 构建了未来互动的想象孪生世界，线上演示可访问：https://quinnnnnne-ai-you.hf.space/。
原文摘要 · Abstract (English)
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}}}.
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。