Social Reality Construction via Active Inference: Modeling the Dialectic of Conformity and Creativity

2026-04-10

AI Summary

Existing computational models struggle to capture the dialectical interplay between norm internalization and creative transformation in social agents. This work proposes a multi-agent simulation framework grounded in active inference to model the endogenous construction of social reality within structured interaction networks. Each agent employs an internal generative model to interact with neighbors, forming social priors and selectively assimilating or innovating new observations. The framework formally unifies the dynamic tension between conformity and individual creativity, revealing a reciprocal co-constitution mechanism between social representations and the distribution of external observations, as well as the self-organizing emergence of cultural niches. Experiments successfully reproduce phenomena including informational convergence, representation–observation co-constitution cycles, and heterogeneous diffusion of creative outputs, thereby validating an endogenous differentiation mechanism underlying shared social reality.

Technology Category

• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Multiagent Systems: Modeling other Agents
• Knowledge Representation and Reasoning: Reasoning with Beliefs

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Social agents both internalize collective norms and reshape them through creative action, yet computational models have not captured this bidirectional process within a unified framework. We propose a multi-agent simulation model grounded in active inference that formalizes the dialectical constitution of social reality on a structured social network. Each agent maintains an internal generative model, communicates with neighbors to form social priors, creates novel observations, and selectively incorporates others'creations into memory. Simulation experiments demonstrate three main findings. First, informationally cohesive social groups emerge endogenously, with representational alignment mirroring the cluster topology of the underlying network. Second, a circular mutual constitution arises between social representations and the observation distribution, maintained through agents'creative acts that project representational structure onto the external world. Third, the propagation of creations exhibits selective, heterogeneous patterns distinct from the stable diffusion of social representations, indicating that agents construct cultural niches through local interaction dynamics. These results suggest that the interplay between social conformity and creative deviation can give rise to the endogenous formation and differentiation of shared social reality.

Problem

• social reality
• active inference
• conformity
• creativity
• multi-agent simulation

Innovation

• active inference
• multi-agent simulation
• social reality construction
• creative deviation
• social conformity