| title | Deep Persona: A Psychologically Grounded Architecture and Evaluation Framework for Role-Playing Agents and Simulations |
|---|---|
| authors | Rotem Dror, Zohar Elyoseph, Yuval Haber, Elad Refoua, Oshrat Ayalon, Adir Solomon |
| date | 2026-09-06 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2609.22255 |
| affiliation | University of Haifa |
| upvotes | 21 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Existing approaches to persona simulation with Large Language Models (LLMs) mostly rely on shallow character descriptions that fail to sustain coherent character behavior across extended interactions. We introduce Deep Persona, a psychologically grounded, three-layered architecture that organizes personas into hierarchical levels of observable expression, latent beliefs, and core motivational drives, for constructing highly convincing role-playing agents. Governed by the principles of scripted determinism and bounded agency, the architecture restricts the model to a reactive engine guided by a structured internal script. We further propose a reference-free evaluation framework that benchmarks dialogue naturalness against empirical human distributions using established psychological clinical instruments and adversarial stress-tests. Empirical evaluation reveals that while LLMs achieve high pragmatic fluency, they exhibit systematic limitations in emotional expression and joint attention. In addition, we present a case study of two Deep Personas and evaluate them using the proposed framework, demonstrating that structured personas can produce interactions that more closely align with human conversational behavior. |
cite
@misc{dror2026deep,
title={Deep Persona: A Psychologically Grounded Architecture and Evaluation Framework for Role-Playing Agents and Simulations},
author={Rotem Dror and Zohar Elyoseph and Yuval Haber and Elad Refoua and Oshrat Ayalon and Adir Solomon},
year={2026},
eprint={2609.22255},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2609.22255}
}