Dynamic Personality Adaptation in Large Language Models via State Machines

2026-02-25

AI Summary

Current large language models struggle to dynamically modulate personality expression during dialogue, limiting their effectiveness in complex interactive scenarios. This work proposes a model-agnostic personality adaptation framework that employs a finite state machine to represent latent personality states, dynamically adjusts state transition probabilities based on conversational context, and leverages a modular personality scoring pipeline to reconstruct system prompts in real time. By integrating state-machine modeling with a dynamic personality evaluation mechanism for the first time, the approach yields a lightweight, plug-and-play architecture compatible with diverse personality models and LLMs. Evaluated in a medical education setting using the interpersonal circumplex model, the framework enables effective personality guidance and de-escalation training, with its lightweight classifier achieving scoring accuracy comparable to that of large models.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

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.

Problem

• personality adaptation
• large language models
• dialogue dynamics
• state machines
• human-computer interaction

Innovation

• dynamic personality adaptation
• state machines
• model-agnostic framework
• personality scoring pipeline
• behavioral alignment