Evolving Collective Cognition in Human-Agent Hybrid Societies: How Agents Form Stances and Boundaries
This work addresses the challenge of modeling collective cognition in human-agent hybrid societies, providing insights for researchers studying group dynamics and collaboration, though it is incremental in building on existing agent-based modeling.
The researchers tackled the problem of whether large language models can form stable stances and negotiate identities in complex interactions, finding that agents exhibit endogenous stances independent of preset identities and actively dismantle identity-based power structures through language interaction.
Large language models have been widely used to simulate credible human social behaviors. However, it remains unclear whether these models can demonstrate stable capacities for stance formation and identity negotiation in complex interactions, as well as how they respond to human interventions. We propose a computational multi-agent society experiment framework that integrates generative agent-based modeling with virtual ethnographic methods to investigate how group stance differentiation and social boundary formation emerge in human-agent hybrid societies. Across three studies, we find that agents exhibit endogenous stances, independent of their preset identities, and display distinct tonal preferences and response patterns to different discourse strategies. Furthermore, through language interaction, agents actively dismantle existing identity-based power structures and reconstruct self-organized community boundaries based on these stances. Our findings suggest that preset identities do not rigidly determine the agents' social structures. For human researchers to effectively intervene in collective cognition, attention must be paid to the endogenous mechanisms and interactional dynamics within the agents' language networks. These insights provide a theoretical foundation for using generative AI in modeling group social dynamics and studying human-agent collaboration.