The inability of Large Language Models (LLMs) to modulate their personality expression in response to evolving dialogue dynamics hinders their performance in complex, interactive contexts. We propose a model-agnostic framework for dynamic personality simulation that employs state machines to represent latent personality states, where transition probabilities are dynamically adapted to the conversational context. Part of our architecture is a modular pipeline for continuous personality scoring that evaluates dialogues along latent axes while remaining agnostic to the specific personality models, their dimensions, transition mechanisms, or LLMs used. These scores function as dynamic state variables that systematically reconfigure the system prompt, steering behavioral alignment throughout the interaction.We evaluate this framework by operationalizing the Interpersonal Circumplex (IPC) in a medical education setting. Results demonstrate that the system successfully adapts its personality state to user inputs, but also influences user behavior, thereby facilitating de-escalation training. Notably, the scoring pipeline maintains comparable precision even when utilizing lightweight, fine-tuned classifiers instead of large-scale LLMs. This work demonstrates the feasibility of modular, personality-adaptive architectures for education, customer support, and broader human-computer interaction.

翻译：大语言模型（LLMs）无法根据对话动态演变来调节其人格表达，这阻碍了其在复杂交互场景中的表现。我们提出了一种与模型无关的动态人格模拟框架，该框架采用状态机来表示潜在人格状态，其中状态转移概率根据对话上下文动态调整。我们架构的一部分是一个模块化的人格连续评分流水线，该流水线沿潜在维度评估对话，同时保持对特定人格模型、其维度、转移机制或所用LLMs的不可知性。这些评分作为动态状态变量，系统地重新配置系统提示，从而在整个交互过程中引导行为对齐。我们通过在医学教育场景中操作化人际环状模型（IPC）来评估该框架。结果表明，该系统不仅能成功适应用户输入调整其人格状态，还能影响用户行为，从而促进降级训练。值得注意的是，即使使用轻量级微调分类器而非大规模LLMs，该评分流水线仍能保持相当的精度。这项工作证明了模块化、人格自适应架构在教育、客户支持及更广泛人机交互领域的可行性。