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

2025-06-04

AI Summary

Existing LLM-based agents lack biologically grounded cognitive architectures, limiting their applicability in digital twin and socially intelligent systems. Method: This paper proposes a multi-agent digital twin framework grounded in the Global Neuronal Workspace Theory (GNWT), integrating cognitively plausible sub-agents for emotion, memory, social norms, and planning. It introduces the first “adventure-style behavioral personality assessment” to mitigate self-report bias and implements a socially intelligent platform supporting bidirectional cultural adaptation—e.g., dating matching and job interview simulation. Results: Experiments on 551 GNWT agents and the Columbia Speed Dating dataset demonstrate strong empirical validity: 72% correlation with human attraction patterns, 77.8% accuracy in match prediction, and 74% inter-rater agreement in human evaluation—establishing the first GNWT-based social AI platform with validated psychological fidelity and cross-cultural functionality.

Technology Category

• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Multiagent Systems: Adversarial Agents
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems

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 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.

Problem

• Implementing Global Workspace Theory in LLM agents for psychological authenticity
• Developing an adventure-based personality test to reduce self-presentation bias
• Creating digital twins for realistic dating and job interview simulations

Innovation

• Implement GNWT for cognitive architecture in LLM agents
• Develop adventure-based personality test to reduce bias
• Create CogniPair platform for realistic social simulations