Deep Persona: A Psychologically Grounded Architecture and Evaluation Framework for Role-Playing Agents and Simulations
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.
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
PersonaArena: Dynamic Simulation for Evaluating and Enhancing Persona-Level Role-Playing in Large Language Models
PersonaArena is a dynamic simulation framework that uses a large corpus of social content and a multi-agent debating judge to evaluate and improve LLMs' ability to maintain coherent and authentic persona-level role-playing in realistic social scenarios.
Beyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM Agents
Introduces Persona Policies (PPol), a plug-and-play control layer that uses LLM-driven evolutionary program search to generate diverse, human-like user personas for evaluating LLM agents. Achieves 33–62% fitness gains over baseline, with human-likeness rated at 80.4%, and improves agent robustness with +17% task success.
Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation
Introduces PALATE, a scalable benchmark for evaluating role-playing agents using person-aligned LLM-simulated users and personalized rubrics, addressing limitations of fixed-history evaluation.
DynSess: Dynamic Session-Level Evaluation and Optimization Framework for Role-Playing Agents
This paper proposes DynSess, a unified session-level evaluation and optimization framework for role-playing agents, addressing the limitation of turn-level metrics by scoring complete dialogue sessions and using session-level rewards to train more coherent character models.
Adversarial Stress Testing of Role-Playing Language Agents using Multi-Agent Evaluation
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.