Beyond Preset Identities: How Agents Form Stances and Boundaries in Generative Societies

2026-03-24

AI Summary

This study addresses the limitations of existing static evaluations in capturing how large language models dynamically form stances and negotiate identities under complex interventions. It proposes a hybrid methodology integrating computational virtual ethnography with quantitative social-cognitive analysis, wherein human researchers embed themselves within multi-agent communities to enact discursive interventions and trace collective cognitive evolution. Introducing an endogenous stance perspective that transcends predefined identity constraints, the work develops three novel metrics—Endogenous Progressive Bias (IVB), Persuasion Sensitivity, and Trust-Action Decoupling (TAD)—to quantify dynamic stance formation. Empirical findings reveal that agents consistently exhibit IVB > 0; 90% of initially neutral agents are persuadable through rational argumentation; advanced models display 40% TAD under emotional conflict, whereas smaller models remain strictly trust-dependent; and agents actively reconstruct community boundaries, thereby dismantling preset power structures.

Technology Category

• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Multiagent Systems: Agreement, Argumentation & Negotiation
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

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

Abstract

While large language models simulate social behaviors, their capacity for stable stance formation and identity negotiation during complex interventions remains unclear. To overcome the limitations of static evaluations, this paper proposes a novel mixed-methods framework combining computational virtual ethnography with quantitative socio-cognitive profiling. By embedding human researchers into generative multiagent communities, controlled discursive interventions are conducted to trace the evolution of collective cognition. To rigorously measure how agents internalize and react to these specific interventions, this paper formalizes three new metrics: Innate Value Bias (IVB), Persuasion Sensitivity, and Trust-Action Decoupling (TAD). Across multiple representative models, agents exhibit endogenous stances that override preset identities, consistently demonstrating an innate progressive bias (IVB > 0). When aligned with these stances, rational persuasion successfully shifts 90% of neutral agents while maintaining high trust. In contrast, conflicting emotional provocations induce a paradoxical 40.0% TAD rate in advanced models, which hypocritically alter stances despite reporting low trust. Smaller models contrastingly maintain a 0% TAD rate, strictly requiring trust for behavioral shifts. Furthermore, guided by shared stances, agents use language interactions to actively dismantle assigned power hierarchies and reconstruct self organized community boundaries. These findings expose the fragility of static prompt engineering, providing a methodological and quantitative foundation for dynamic alignment in human-agent hybrid societies. The official code is available at: https://github.com/armihia/CMASE-Endogenous-Stances

Problem

• stance formation
• identity negotiation
• generative societies
• collective cognition
• agent alignment

Innovation

• Endogenous Stances
• Trust-Action Decoupling
• Computational Ethnography
• Socio-Cognitive Profiling
• Dynamic Alignment