While both agent interaction and personalisation are vibrant topics in research on large language models (LLMs), there has been limited focus on the effect of language interaction on the behaviour of persona-conditioned LLM agents. Such an endeavour is important to ensure that agents remain consistent to their assigned traits yet are able to engage in open, naturalistic dialogues. In our experiments, we condition GPT-3.5 on personality profiles through prompting and create a two-group population of LLM agents using a simple variability-inducing sampling algorithm. We then administer personality tests and submit the agents to a collaborative writing task, finding that different profiles exhibit different degrees of personality consistency and linguistic alignment to their conversational partners. Our study seeks to lay the groundwork for better understanding of dialogue-based interaction between LLMs and highlights the need for new approaches to crafting robust, more human-like LLM personas for interactive environments.

我们在GPT-3.5上通过提示方式进行个性化训练，创建了一组双组群体的LLM代理，然后进行个性测试并将代理提交到协作写作任务中，发现不同个性表现出不同程度的人格一致性和语言对话伙伴的语言协调性。我们的研究旨在为更好地理解LLMs之间基于对话的交互奠定基础，并强调了在交互环境中塑造稳健且更具人性的LLM个性的新方法的需求。

互动中的LLM Agents：大型语言模型互动群体中个性一致性和语言对齐的测量