CogniPair: From LLM Chatbots to Conscious AI Agents -- GNWT-Based Multi-Agent Digital Twins for Social Pairing -- Dating & Hiring Applications

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ye, Wanghao, Chen, Sihan, Wang, Yiting, He, Shwai, Tian, Bowei, Sun, Guoheng, Wang, Ziyi, Wang, Ziyao, He, Yexiao, Shen, Zheyu, Liu, Meng, Zhang, Yuning, Feng, Meng, Wang, Yang, Peng, Siyuan, Dai, Yilong, Duan, Zhenle, Xiong, Lang, Liu, Joshua, Qin, Hanzhang, Li, Ang
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computers and Society Multiagent Systems
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866911293228711936
author	Ye, Wanghao Chen, Sihan Wang, Yiting He, Shwai Tian, Bowei Sun, Guoheng Wang, Ziyi Wang, Ziyao He, Yexiao Shen, Zheyu Liu, Meng Zhang, Yuning Feng, Meng Wang, Yang Peng, Siyuan Dai, Yilong Duan, Zhenle Xiong, Lang Liu, Joshua Qin, Hanzhang Li, Ang
author_facet	Ye, Wanghao Chen, Sihan Wang, Yiting He, Shwai Tian, Bowei Sun, Guoheng Wang, Ziyi Wang, Ziyao He, Yexiao Shen, Zheyu Liu, Meng Zhang, Yuning Feng, Meng Wang, Yang Peng, Siyuan Dai, Yilong Duan, Zhenle Xiong, Lang Liu, Joshua Qin, Hanzhang Li, Ang
contents	Current large language model (LLM) agents lack authentic human psychological processes necessary for genuine digital twins and social AI applications. To address this limitation, we present a computational implementation of Global Workspace Theory (GNWT) that integrates human cognitive architecture principles into LLM agents, creating specialized sub-agents for emotion, memory, social norms, planning, and goal-tracking coordinated through a global workspace mechanism. However, authentic digital twins require accurate personality initialization. We therefore develop a novel adventure-based personality test that evaluates true personality through behavioral choices within interactive scenarios, bypassing self-presentation bias found in traditional assessments. Building on these innovations, our CogniPair platform enables digital twins to engage in realistic simulated dating interactions and job interviews before real encounters, providing bidirectional cultural fit assessment for both romantic compatibility and workplace matching. Validation using 551 GNWT-Agents and Columbia University Speed Dating dataset demonstrates 72% correlation with human attraction patterns, 77.8% match prediction accuracy, and 74% agreement in human validation studies. This work advances psychological authenticity in LLM agents and establishes a foundation for intelligent dating platforms and HR technology solutions.
format	Preprint
id	arxiv_https___arxiv_org_abs_2506_03543
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	CogniPair: From LLM Chatbots to Conscious AI Agents -- GNWT-Based Multi-Agent Digital Twins for Social Pairing -- Dating & Hiring Applications Ye, Wanghao Chen, Sihan Wang, Yiting He, Shwai Tian, Bowei Sun, Guoheng Wang, Ziyi Wang, Ziyao He, Yexiao Shen, Zheyu Liu, Meng Zhang, Yuning Feng, Meng Wang, Yang Peng, Siyuan Dai, Yilong Duan, Zhenle Xiong, Lang Liu, Joshua Qin, Hanzhang Li, Ang Artificial Intelligence Computers and Society Multiagent Systems Current large language model (LLM) agents lack authentic human psychological processes necessary for genuine digital twins and social AI applications. To address this limitation, we present a computational implementation of Global Workspace Theory (GNWT) that integrates human cognitive architecture principles into LLM agents, creating specialized sub-agents for emotion, memory, social norms, planning, and goal-tracking coordinated through a global workspace mechanism. However, authentic digital twins require accurate personality initialization. We therefore develop a novel adventure-based personality test that evaluates true personality through behavioral choices within interactive scenarios, bypassing self-presentation bias found in traditional assessments. Building on these innovations, our CogniPair platform enables digital twins to engage in realistic simulated dating interactions and job interviews before real encounters, providing bidirectional cultural fit assessment for both romantic compatibility and workplace matching. Validation using 551 GNWT-Agents and Columbia University Speed Dating dataset demonstrates 72% correlation with human attraction patterns, 77.8% match prediction accuracy, and 74% agreement in human validation studies. This work advances psychological authenticity in LLM agents and establishes a foundation for intelligent dating platforms and HR technology solutions.
title	CogniPair: From LLM Chatbots to Conscious AI Agents -- GNWT-Based Multi-Agent Digital Twins for Social Pairing -- Dating & Hiring Applications
topic	Artificial Intelligence Computers and Society Multiagent Systems
url	https://arxiv.org/abs/2506.03543