Emergent Relational Order in LLM Agent Societies: From Collective Affect to Authority Stratification

2026-06-22

AI Summary

This study investigates the mechanistic foundations of Fei Xiaotong’s “differential mode of association” and simulates its emergence through long-term multi-agent interactions. Building upon affect control theory, social identity theory, and Durkheimian collective sentiments, the authors develop the CAREB-MAS multi-agent framework, which integrates an emotion–ethics–belief reasoning chain and dynamic egocentric identities to drive social interaction within an environment defined solely by individual production and preference-based allocation. For the first time in a large language model–driven multi-agent system, the model successfully reproduces five core phenomena of the differential mode: stable division of labor, relational economic ethics, decay of cooperation with relational distance, emergence of relational authority, and lineage-based center–periphery stratification. The findings suggest that culturally specific social structures may arise as emergent outcomes of universal social mechanisms and illuminate how shifts in production structures catalyze a transition in social integration from kinship ties toward functional interdependence.

Abstract

Fei Xiaotong's Differential Order Pattern characterizes rural society as egocentric and relationally graded, with cooperation attenuating over social distance. Although often treated as culturally specific, its mechanistic basis remains under-operationalized, and prior LLM-based simulations have mainly addressed short-term coordination rather than long-horizon social structure. We propose CAREB-MAS, a multi-agent framework grounded in Affect Control Theory, Social Identity Theory, and Durkheimian collective affect. Agents reason through an emotion-ethics-belief chain and maintain dynamically evolving egocentric identities, while the macro environment specifies only individual production, preference-based allocation, and minimal interaction protocols. Across long-horizon simulations, agents spontaneously reproduce five core Differential Order phenomena: stable labor specialization, guanxi-based economic ethics, relational decay of cooperation, emergent relational authority, and clan-based center-periphery stratification. These patterns shift with production structure from kin-centered integration toward greater functional interdependence. Extensive experiment results support interpreting Differential Order as a structure-sensitive emergent outcome of general social mechanisms, with LLM-based multi-agent simulation providing an interdisciplinary framework for studying social structure and change.

Problem

• Differential Order Pattern
• social structure
• LLM agent societies
• emergent phenomena
• collective affect

Innovation

• LLM-based multi-agent simulation
• emergent social structure
• Affect Control Theory
• Differential Order Pattern
• relational authority