CogniPair: From LLM Chatbots to Conscious AI Agents -- GNWT-Based Multi-Agent Digital Twins for Social Pairing -- Dating & Hiring Applications
Wanghao Ye, Sihan Chen, Yiting Wang, Shwai He, Bowei Tian, Guoheng Sun, Ziyi Wang, Ziyao Wang, Yexiao He, Zheyu Shen, Meng Liu, Yuning Zhang, Meng Feng, Yang Wang, Siyuan Peng, Yilong Dai, Zhenle Duan, Lang Xiong, Joshua Liu, Hanzhang Qin, and Ang Li

TL;DR
This paper introduces CogniPair, a GNWT-based multi-agent system that creates psychologically authentic digital twins for social applications like dating and hiring, achieving high correlation with human preferences.
Contribution
It develops a novel GNWT implementation for LLM agents, introduces an adventure-based personality test, and demonstrates realistic social interactions with high predictive accuracy.
Findings
72% correlation with human attraction patterns
77.8% match prediction accuracy
74% agreement in human validation studies
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsPersonality Traits and Psychology · Evolutionary Psychology and Human Behavior · AI in Service Interactions
MethodsSPEED: Separable Pyramidal Pooling EncodEr-Decoder for Real-Time Monocular Depth Estimation on Low-Resource Settings
