Large Language Models (LLMs) can be deployed in situations where they process positive/negative interactions with other agents. We study how this is done under the sociological framework of social balance, which explains the emergence of one faction or multiple antagonistic ones among agents. Across different LLM models, we find that balance depends on the (i) type of interaction, (ii) update mechanism, and (iii) population size. Across (i)-(iii), we characterize the frequency at which social balance is achieved, the justifications for the social dynamics, and the diversity and stability of interactions. Finally, we explain how our findings inform the deployment of agentic systems.

翻译：大型语言模型（LLMs）可被部署于处理与其他智能体之间正/负交互的情境中。本研究在社会平衡的社会学框架下探讨这一过程，该框架解释了智能体间单一派系或多个对立派系的形成机制。通过对不同LLM模型的实验，我们发现平衡状态取决于：（i）交互类型，（ii）更新机制，以及（iii）群体规模。基于对（i）-（iii）的系统分析，我们量化了达成社会平衡的频率，阐释了社会动态的合理性依据，并揭示了交互模式的多样性与稳定性特征。最后，我们论证了本研究结论对智能体系统部署的指导意义。