Skip to content

Deep Persona: A Psychologically Grounded Architecture and Evaluation Framework for Role-Playing Agents and Simulations

Sep 2026 · 0 citations · 44 references
Computer Science

TL;DR

Deep Persona is introduced, 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.

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.

View source

Similar papers

Preprint Aug 2026

Do LLMs Understand Personality? Rethinking Persona Fidelity Evaluation through Structured Behavioral Inference

This work proposes PRISM (Persona Reasoning with Inverse SFL-based Modeling), a psycholinguistically grounded framework that reformulates persona fidelity evaluation as a structured inverse inference task, providing a more reliable framework for persona fidelity evaluation.

Meng-Fan Li, Ze-Sheng Wei, Xuan-Hua Shi et al. · 1 citation
#natural language process... Open access Sep 2026

PERSONAWEAVER: Controllable Diversity Beyond Conventional Archetypes in Procedural Character Generation

PersonaWeaver is introduced, which disentangles world building from behavioral specification and models behavior through setting general, diverse, manually curated banks of moral positions and conversational reactions and allows us to test how far LLM(s) can be pushed beyond their default behavioral patterns across set...

Maan Qraitem, Kate Saenko, Bryan A. Plummer · 0 citations
Preprint Oct 2026

Enhancing LLMs with Cognitive-Affective Personality Inference for Simulating Human Social-Psychological Behavior

SPIN is introduced, a cognitive-affective personality system-inspired inference pipeline for simulating human social-psychological behavior that suggests that structured personality-state inference can improve benchmark-level behavioral alignment beyond richer persona descriptions or generic multi-step reasoning.

Zhi-Bo Deng, Dong-Yuan Li, Shu-Wen Ge et al. · 0 citations
#artificial intelligence Preprint Oct 2026

MASC: A Multi-Agent Self-Calibration Framework with Latent Construct Alignment for Consistent Client Role-Playing in Psychological Counseling

Large language models are increasingly used to simulate clients for counselor training and psychological counseling research, but reliable simulation requires clients to remain psychologically coherent across extended interactions. Existing role-playing methods largely rely on static profile prompts and may exhibit per...

Shi-Xin Peng, Kun Jiang, Jia-Xing Zheng et al. · 0 citations

Do Personality-Tuned LLMs Make Better Social Agents?

This work investigates whether personality-aware fine-tuning can reduce the consistency and controllability of personality-conditioned dialogue generation compared with instruction prompting alone, and indicates that fine-tuned models are not better at role-playing different personalities than their respective baseline...

Tim Krabbe, Xiao-Dan Shi · 0 citations
#machine learning Book Open access Sep 2026

Multimodal Detection of Higher-Order Behavioral Constructs: Self-Compassion in Structured Reflective Interactions

Many of the qualities that matter most in how people learn and grow, how someone regulates their emotions, reflects on a setback, or stays aware of others during a difficult conversation, are not directly observable. They have to be inferred from how someone speaks, moves, and sounds over time, and they resist the kind...

Siddhant Jain, Dimitra Tsovaltzi · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.