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

Hugging Face Daily Papers Papers

Summary

This paper introduces Deep Persona, a psychologically grounded architecture for role-playing agents, and proposes an evaluation framework. It evaluates LLMs and finds systematic limitations in emotional expression despite high pragmatic fluency.

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.
Original Article
View Cached Full Text

Cached at: 09/22/26, 07:25 AM

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

Source: https://huggingface.co/papers/2609.22255

Abstract

ExistingapproachestopersonasimulationwithLargeLanguageModels(LLMs)mostlyrelyonshallowcharacterdescriptionsthatfailtosustaincoherentcharacterbehavioracrossextendedinteractions.WeintroduceDeepPersona,apsychologicallygrounded,three-layeredarchitecturethatorganizespersonasintohierarchicallevelsofobservableexpression,latentbeliefs,andcoremotivationaldrives,forconstructinghighlyconvincingrole-playingagents.Governedbytheprinciplesofscripteddeterminismandboundedagency,thearchitecturerestrictsthemodeltoareactiveengineguidedbyastructuredinternalscript.Wefurtherproposeareference-freeevaluationframeworkthatbenchmarksdialoguenaturalnessagainstempiricalhumandistributionsusingestablishedpsychologicalclinicalinstrumentsandadversarialstress-tests.EmpiricalevaluationrevealsthatwhileLLMsachievehighpragmaticfluency,theyexhibitsystematiclimitationsinemotionalexpressionandjointattention.Inaddition,wepresentacasestudyoftwoDeepPersonasandevaluatethemusingtheproposedframework,demonstratingthatstructuredpersonascanproduceinteractionsthatmorecloselyalignwithhumanconversationalbehavior.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2609\.22255

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2609.22255 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.22255 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.22255 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Adversarial Stress Testing of Role-Playing Language Agents using Multi-Agent Evaluation

arXiv cs.AI

This paper presents a modular multi-agent platform for adversarially stress-testing role-playing language agents, using a strategy-driven Interrogator Agent and automated Judging Agent to reveal cumulative behavioral failures across multi-turn dialogues. Experiments across three personas and LLM families show multi-strategy adversarial evaluation reduces robustness scores by 0.17-0.20 and identifies common failure patterns, with strong human alignment.