🤖 AI Summary
This study addresses the lack of a unified framework for explaining the emergence of social relationships and social intelligence in long-term human–AI interaction. Modeling human–AI dialogue as a self-organizing socio-cognitive system, this work integrates affective adaptation, relational structuring, social memory, and personality consistency to propose novel theoretical constructs—including multi-timescale cognition, relational attractors, trust basins, developmental phase transitions, and socio-cognitive energy dynamics. Leveraging 14,700 dialogue turns and combining dynamical systems modeling with theory-driven empirical analysis, the research reveals hierarchical temporal persistence in social cognition, stable relational attractors, phase-transition-like developmental patterns, and a structured energy landscape. Notably, social intelligence exhibits a significant negative correlation with cognitive energy (r = –0.391, p < 0.001), and interactions demonstrate a consistent trend of energy decay over time.
📝 Abstract
Current conversational AI systems have made significant progress in language generation, personalization, and long-context interaction. However, most existing methods model social behavior through isolated components such as emotion modeling, memory retrieval, or persona conditioning, lacking a unified framework to explain the emergence of stable social relationships and social intelligence in long-term human-AI interaction.To address this, we propose the Human-AI Coevolution Dynamics Framework (HACD-H), a formal model of human-AI interaction as a self-organizing social cognitive system. HACD-H integrates emotional adaptation, relational organization, social memory, and personality consistency into a unified dynamical framework and introduces principles including multi-timescale social cognition, relational attractors, trust basins, developmental phase transitions, and social cognitive energy dynamics.We construct a conversational dataset with approximately 14,700 interaction turns and develop a theory-driven empirical evaluation framework. Results reveal a hierarchy of temporal persistence in social cognition, stable relational attractors, phase-transition-like developmental patterns, and a structured social cognitive energy landscape. Social intelligence shows a significant negative correlation with social cognitive energy (r = -0.391, p < 0.001), and interaction trajectories exhibit progressive energy reduction over time.These findings suggest that social intelligence emerges from long-term social cognitive coevolution rather than isolated conversational capabilities. HACD-H provides a unified theoretical foundation for modeling adaptive human-AI social interaction and developing socially intelligent AI systems.