AI YOU Town: Make Friends and Money with Your Digital Twin

2026-07-11

AI Summary

This work addresses the limitations of existing user personality modeling approaches, which rely on static prompts, lack proper uncertainty calibration, and neglect temporal evidence—leading to personality drift in extended dialogues. To overcome these issues, the authors propose the AI YOU framework, which integrates dynamic prompt engineering, Bayesian personality updating, and conformal prediction to enable continuous inference of a 22-dimensional personality profile. The framework further incorporates a three-tiered cognitive memory architecture with periodic memory anchor points to ensure long-term personality consistency during prolonged interactions. Experimental results demonstrate that, in hundred-turn role-playing dialogues, the method achieves conformal coverage rates of 0.921–0.976, significantly outperforming baseline models while effectively mitigating personality drift and enhancing both uncertainty calibration and memory-driven reasoning capabilities.

Abstract

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}}}.

Problem

• persona consistency
• trait drift
• uncertainty calibration
• long-term interaction
• digital twin

Innovation

• digital twin
• Bayesian updating
• conformal prediction
• persona consistency
• cognitive memory