# Dynamic Personality Adaptation in Large Language Models via State Machines

arXiv: https://arxiv.org/abs/2602.22157 · HTML: https://mlsanity.com/paper/2602.22157/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 40 references that are in the map.
- First posted on arXiv 25 Feb 2026.

## Builds on (most cited first, 19 of 19)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Personality Traits in Large Language Models](https://mlsanity.com/paper/2307.00184/) (2023)
- [BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data](https://mlsanity.com/paper/2410.16491/) (2024)
- [Identifying and Manipulating the Personality Traits of Language Models](https://mlsanity.com/paper/2212.10276/) (2022)
- [Seamless Interaction: Dyadic Audiovisual Motion Modeling and Large-Scale Dataset](https://mlsanity.com/paper/2506.22554/) (2025)
- [LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models](https://mlsanity.com/paper/2402.02896/) (2024)
- [Limited Ability of LLMs to Simulate Human Psychological Behaviours: a Psychometric Analysis](https://mlsanity.com/paper/2405.07248/) (2024)
- [Large Language Models Do Not Simulate Human Psychology](https://mlsanity.com/paper/2508.06950/) (2025)
- [Evolving Agents: Interactive Simulation of Dynamic and Diverse Human Personalities](https://mlsanity.com/paper/2404.02718/) (2024)
- [Self-assessment, Exhibition, and Recognition: a Review of Personality in Large Language Models](https://mlsanity.com/paper/2406.17624/) (2024)
- [Native vs Non-Native Language Prompting: A Comparative Analysis](https://mlsanity.com/paper/2409.07054/) (2024)
- [The Dark Patterns of Personalized Persuasion in Large Language Models: Exposing Persuasive Linguistic Features for Big Five Personality Traits in LLMs Responses](https://mlsanity.com/paper/2411.06008/) (2024)
- [Less but Better: Parameter-Efficient Fine-Tuning of Large Language Models for Personality Detection](https://mlsanity.com/paper/2504.05411/) (2025)
- [Can ChatGPT Read Who You Are?](https://mlsanity.com/paper/2312.16070/) (2023)
- [PsychAdapter: Adapting LLM Transformers to Reflect Traits, Personality and Mental Health](https://mlsanity.com/paper/2412.16882/) (2024)
- [PersonaFuse: A Personality Activation-Driven Framework for Enhancing Human-LLM Interactions](https://mlsanity.com/paper/2509.07370/) (2025)
- [Scaling Personality Control in LLMs with Big Five Scaler Prompts](https://mlsanity.com/paper/2508.06149/) (2025)
- [Personality Differences Drive Conversational Dynamics: A High-Dimensional NLP Approach](https://mlsanity.com/paper/2410.11043/) (2024)

## Built on by (most cited first, 2 of 2)

- [PHASE-Tree: Modeling Character-State Evolution in Long-Horizon Role-Playing Dialogue](https://mlsanity.com/paper/2608.06975/) (2026)
- [Emergi-PersonaOS: A Persona Agent Operating System for Situational Adaptation and Controllable Evolution](https://mlsanity.com/paper/2609.27417/) (2026)

## Abstract (arXiv)

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.