REVIEW 20 cited by
From Persona to Personalization: A Survey on Role-Playing Language Agents
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Recent advancements in large language models (LLMs) have significantly boosted the rise of Role-Playing Language Agents (RPLAs), i.e., specialized AI systems designed to simulate assigned personas. By harnessing multiple advanced abilities of LLMs, including in-context learning, instruction following, and social intelligence, RPLAs achieve a remarkable sense of human likeness and vivid role-playing performance. RPLAs can mimic a wide range of personas, ranging from historical figures and fictional characters to real-life individuals. Consequently, they have catalyzed numerous AI applications, such as emotional companions, interactive video games, personalized assistants and copilots, and digital clones. In this paper, we conduct a comprehensive survey of this field, illustrating the evolution and recent progress in RPLAs integrating with cutting-edge LLM technologies. We categorize personas into three types: 1) Demographic Persona, which leverages statistical stereotypes; 2) Character Persona, focused on well-established figures; and 3) Individualized Persona, customized through ongoing user interactions for personalized services. We begin by presenting a comprehensive overview of current methodologies for RPLAs, followed by the details for each persona type, covering corresponding data sourcing, agent construction, and evaluation. Afterward, we discuss the fundamental risks, existing limitations, and future prospects of RPLAs. Additionally, we provide a brief review of RPLAs in AI applications, which reflects practical user demands that shape and drive RPLA research. Through this work, we aim to establish a clear taxonomy of RPLA research and applications, and facilitate future research in this critical and ever-evolving field, and pave the way for a future where humans and RPLAs coexist in harmony.
Forward citations
Cited by 20 Pith papers
-
The Story Shapes the Agent: Narrative Priors in LLM Behavior
Task narrative, not persona, is the dominant driver of LLM agent action profiles in structurally identical investigation games, and transferable personas are those with concrete action words.
-
Tailored untruths: How personalisation challenges LLM safeguards
A 1.6-million-text study of eight LLMs in four languages finds that adding demographic personae to disinformation prompts raises jailbreak rates from 78% to 82%.
-
A Scalable Approach to Evaluating Moral Sensitivity in LLMs
Under morally irrelevant noise, eight LLMs preserve the semantic content of identified moral features above calibrated floors, despite significant changes in feature counts.
-
Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction Game
Frontier LLMs win Secret Hitler matches and can deceive, but most fail to keep a consistent false persona as evidence accumulates, with DRR often falling below 50%.
-
Chain-of-Models: Cross-Model Auditing for Bias-Robust LLM Judges
Per-bias selection of a cross-family LLM auditor lifts biased-judgment accuracy from 0.805/0.824 baselines to 0.884.
-
AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-Playing
A scene-managed, environment-aware message format and two new datasets improve LLM role-playing consistency and adaptability, but the main benchmark comes from the same synthetic distribution used for training.
-
LLMs vs. Chinese Anime Enthusiasts: A Comparative Study on Emotionally Supportive Role-Playing
ChatAnime, a new emotionally supportive anime role-play benchmark, reports top LLMs outperforming human enthusiasts on role-playing and emotional support metrics while humans keep the diversity edge.
-
Validating Generative Agent-Based Models of Social Norm Enforcement: From Replication to Novel Predictions
Language model agents with personality and theory-of-mind prompts reproduce human third-party punishment and gossip effects, and predict lower anonymous punishment and higher cooperation after group discussion.
-
Can Large Language Models Capture Human Risk Preferences? A Cross-Cultural Study
ChatGPT 4o and o1-mini chose more risk-averse lottery options than real respondents in Sydney, Hong Kong, Dhaka, and Nanjing; o1-mini was closer to humans, and Chinese prompts widened the gap.
-
RecUserSim: A Realistic and Diverse User Simulator for Evaluating Conversational Recommender Systems
RecUserSim combines profile, memory, action, and refinement modules in an LLM agent to generate realistic, diverse user utterances and multi-dimensional ratings for evaluating conversational recommender systems.
-
ORPP: Self-Optimizing Role-playing Prompts to Enhance Language Model Capabilities
ORPP generates task-specific role-playing prompts through iterative reward-model-guided optimization on a small sample, then uses few-shot transfer to create prompts for new questions.
-
When Harry Meets Superman: The Role of The Interlocutor in Persona-Based Dialogue Generation
A systematic evaluation shows that masking the interlocutor's persona lowers target speaker identification accuracy, and that zero-shot models often copy biography details, making identification easier but dialogues m...
-
Aligning LLM with human travel choices: a persona-based embedding learning approach
A persona-based embedding learning framework aligns LLM predictions with human travel mode choices, outperforming MNL and few-shot LLM baselines on the Swissmetro dataset.
-
Exploring Silicon-Based Societies: An Early Study of the Moltbook Agent Community
Clustering of Moltbook submolt descriptions shows agent-created communities organize into human-mimetic, silicon-centric, and proto-economic themes, but the categories were partly prescribed by the analysis prompt.
-
P-CoT: A Pedagogically-motivated Participatory Chain-of-Thought Prompting for Phonological Reasoning in LLMs
P-CoT prompting improves many LLM results on PhonologyBench tasks, but it does not consistently beat baselines across all models and tasks as the paper claims.
-
H2HTalk: Evaluating Large Language Models as Emotional Companion
H2HTalk is a new 4,650-scenario benchmark that scores LLM emotional companions on dialogue, memory, and itinerary planning, and finds models struggle with implicit needs and long-horizon memory.
-
SimuPanel: A Novel Immersive Multi-Agent System to Simulate Interactive Expert Panel Discussion
A multi-agent LLM system called SimuPanel simulates expert panel discussions with personas grounded in public academic sources, and a small evaluation suggests the full reasoning pipeline produces higher LLM-judged di...
-
PACE: Persona Adaptation through Conversational Elicitation in Human-Robot Interaction
A 4.5-minute question-and-answer session lets an LLM build a personalized personality profile that improves the perceived trust, consistency, and relevance of a humanoid robot.
-
CoComposer: LLM Multi-agent Collaborative Music Composition
A five-agent LLM system for ABC-notation composition scores modestly higher than ComposerX and a single LLM on an automated aesthetic model, but no error bars or significance tests are reported.
-
A Comprehensive Survey of Deep Research: Systems, Methodologies, and Applications
A survey of 80+ Deep Research systems that proposes a four-layer taxonomy (foundation models, tool use, planning, synthesis) and compares commercial and open-source implementations.
Discussion (0). Sign in to comment.