Fame Fades, Nature Remains: Disentangling the Character Identity of Role-Playing Agents

• URL: http://arxiv.org/abs/2601.04716v1
• Date: Thu, 08 Jan 2026 08:33:40 GMT
• Title: Fame Fades, Nature Remains: Disentangling the Character Identity of Role-Playing Agents
• Authors: Yonghyun Jun, Junhyuk Choi, Jihyeong Park, Hwanhee Lee,
• Abstract summary: We propose a multidimensional construct that disentangles a character into two distinct layers: textbf(1) Parametric Identity, referring to character-specific knowledge encoded from the LLM's pre-training, and textbf(2) Attributive Identity, capturing fine-grained behavioral properties such as personality traits and moral values.<n>Our findings pinpoint negative social natures as the primary bottleneck in RPA fidelity, guiding future character construction and evaluation.
• Score: 13.029517493304505
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite the rapid proliferation of Role-Playing Agents (RPAs) based on Large Language Models (LLMs), the structural dimensions defining a character's identity remain weakly formalized, often treating characters as arbitrary text inputs. In this paper, we propose the concept of \textbf{Character Identity}, a multidimensional construct that disentangles a character into two distinct layers: \textbf{(1) Parametric Identity}, referring to character-specific knowledge encoded from the LLM's pre-training, and \textbf{(2) Attributive Identity}, capturing fine-grained behavioral properties such as personality traits and moral values. To systematically investigate these layers, we construct a unified character profile schema and generate both Famous and Synthetic characters under identical structural constraints. Our evaluation across single-turn and multi-turn interactions reveals two critical phenomena. First, we identify \textit{"Fame Fades"}: while famous characters hold a significant advantage in initial turns due to parametric knowledge, this edge rapidly vanishes as models prioritize accumulating conversational context over pre-trained priors. Second, we find that \textit{"Nature Remains"}: while models robustly portray general personality traits regardless of polarity, RPA performance is highly sensitive to the valence of morality and interpersonal relationships. Our findings pinpoint negative social natures as the primary bottleneck in RPA fidelity, guiding future character construction and evaluation.

Related papers

• Rethinking Role-Playing Evaluation: Anonymous Benchmarking and a Systematic Study of Personality Effects [21.364811854827163]
  Large language models (LLMs) have demonstrated significant potential in developing Role-Playing Agents (RPAs)<n>Current research primarily evaluates RPAs using famous fictional characters.<n>This dependency creates a bias that limits the generalization of RPAs to unseen personas.<n>This work establishes a fairer evaluation protocol and validates a scalable, personality-enhanced framework for constructing robust RPAs.
  arXiv  Detail & Related papers  (2026-03-04T10:24:02Z)
• Breaking the Assistant Mold: Modeling Behavioral Variation in LLM Based Procedural Character Generation [62.54606886226136]
  Procedural content generation has enabled vast virtual worlds through levels, maps, and quests, but large-scale character generation remains underexplored.<n>We identify two alignment-induced biases in existing methods.<n>We introduce PersonaWeaver, a framework that disentangles world-building from behavioral-building.
  arXiv  Detail & Related papers  (2026-01-06T20:18:01Z)
• PsyAgent: Constructing Human-like Agents Based on Psychological Modeling and Contextual Interaction [4.663685189987781]
  We present PsyAgent, which couples a Big Five trait prior with Bourdieu's cognitive-social co-structure.<n>PsyAgent comprises: (i) Individual Structure (IS), a machine-usable profile encoding traits and facets, cognitive style, values, cultural and educational capital, and salient life episodes; and (ii) Multi-Scenario Contexting (MSC), role-relationship-norm frames spanning eight arenas.
  arXiv  Detail & Related papers  (2026-01-06T11:14:03Z)
• Dynamic Context Adaptation for Consistent Role-Playing Agents with Retrieval-Augmented Generations [1.1740676332544449]
  We propose Amadeus, a training-free framework for role-playing agents (RPAs)<n>A Amadeus framework can significantly enhance persona consistency even when responding to questions that lie beyond a character's knowledge.
  arXiv  Detail & Related papers  (2025-08-04T03:27:05Z)
• Traits Run Deep: Enhancing Personality Assessment via Psychology-Guided LLM Representations and Multimodal Apparent Behaviors [46.55948528317124]
  We propose a novel personality assessment framework called textittextbfTraits Run Deep.<n>It employs textittextbfpsychology-informed prompts to elicit high-level personality-relevant semantic representations.<n>It devises a textittextbfText-Centric Trait Fusion Network that anchors rich text semantics to align and integrate asynchronous signals from other modalities.
  arXiv  Detail & Related papers  (2025-07-30T04:12:14Z)
• CharacterBench: Benchmarking Character Customization of Large Language Models [80.29164862682063]
  We propose CharacterBench, the largest bilingual generative benchmark, with 22,859 human-annotated samples covering 3,956 characters.<n>We define 11 dimensions of 6 aspects, classified as sparse and dense dimensions based on whether character features evaluated by specific dimensions manifest in each response.<n>We also develop CharacterJudge model for cost-effective and stable evaluations.
  arXiv  Detail & Related papers  (2024-12-16T15:55:34Z)
• CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds [74.02480671181685]
  Role-playing is a crucial capability of Large Language Models (LLMs)<n>Current evaluation methods fall short of adequately capturing the nuanced character traits and behaviors essential for authentic role-playing.<n>We propose CharacterBox, a simulation sandbox designed to generate situational fine-grained character behavior trajectories.
  arXiv  Detail & Related papers  (2024-12-07T12:09:35Z)
• CHATTER: A Character Attribution Dataset for Narrative Understanding [31.540540919042154]
  We validate a subset of CHATTER, called CHATTEREVAL, using human annotations to serve as a benchmark to evaluate the character attribution task in movie scripts.<n>evaldataset also assesses narrative understanding and the long-context modeling capacity of language models.
  arXiv  Detail & Related papers  (2024-11-07T22:37:30Z)
• Revealing Personality Traits: A New Benchmark Dataset for Explainable Personality Recognition on Dialogues [63.936654900356004]
  Personality recognition aims to identify the personality traits implied in user data such as dialogues and social media posts. We propose a novel task named Explainable Personality Recognition, aiming to reveal the reasoning process as supporting evidence of the personality trait.
  arXiv  Detail & Related papers  (2024-09-29T14:41:43Z)
• Is persona enough for personality? Using ChatGPT to reconstruct an agent's latent personality from simple descriptions [2.6080756513915824]
  Personality, a fundamental aspect of human cognition, contains a range of traits that influence behaviors, thoughts, and emotions. This paper explores the capabilities of large language models (LLMs) in reconstructing these complex cognitive attributes based only on simple descriptions containing socio-demographic and personality type information.
  arXiv  Detail & Related papers  (2024-06-18T02:32:57Z)
• CHIRON: Rich Character Representations in Long-Form Narratives [98.273323001781]
  We propose CHIRON, a new character sheet' based representation that organizes and filters textual information about characters.<n>We validate CHIRON via the downstream task of masked-character prediction, where our experiments show CHIRON is better and more flexible than comparable summary-based baselines.<n> metrics derived from CHIRON can be used to automatically infer character-centricity in stories, and that these metrics align with human judgments.
  arXiv  Detail & Related papers  (2024-06-14T17:23:57Z)
• CharacterGPT: A Persona Reconstruction Framework for Role-Playing Agents [6.220415006158471]
  We introduce CharacterGPT, a framework designed to dynamically reconstruct character personas through Character Persona Training (CPT)<n>This approach incrementally updates personas by extracting traits from chapter-wise novel summaries, reflecting the progression of the narrative.<n>Our framework is evaluated through Big Five personality evaluations and creative tasks, in which characters generate original narratives.
  arXiv  Detail & Related papers  (2024-05-30T07:44:16Z)
• CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models [66.4382820107453]
  We present CharacterGLM, a series of models built upon ChatGLM, with model sizes ranging from 6B to 66B parameters. Our CharacterGLM is designed for generating Character-based Dialogues (CharacterDial), which aims to equip a conversational AI system with character customization for satisfying people's inherent social desires and emotional needs.
  arXiv  Detail & Related papers  (2023-11-28T14:49:23Z)
• InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews [57.04431594769461]
  This paper introduces a novel perspective to evaluate the personality fidelity of RPAs with psychological scales. Experiments include various types of RPAs and LLMs, covering 32 distinct characters on 14 widely used psychological scales. With InCharacter, we show that state-of-the-art RPAs exhibit personalities highly aligned with the human-perceived personalities of the characters, achieving an accuracy up to 80.7%.
  arXiv  Detail & Related papers  (2023-10-27T08:42:18Z)
• Identity-Aware Semi-Supervised Learning for Comic Character Re-Identification [2.4624325014867763]
  We introduce a robust framework that combines metric learning with a novel 'Identity-Aware' self-supervision method. Our approach involves processing both facial and bodily features within a unified network architecture. By extensively validating our method using in-series and inter-series evaluation metrics, we demonstrate its effectiveness in consistently re-identifying comic characters.
  arXiv  Detail & Related papers  (2023-08-17T16:48:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.