mlsanityData to 14 Oct 2026

From Persona to Personalization: A Survey on Role-Playing Language Agents

arXiv 2404.18231 ↗First posted 28 Apr 2024cs.CL cs.AIcited by 212

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

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.

Key facts. Cited by 212 papers in the map (data through 14 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 214 of its 289 references that are in the map. First posted on arXiv 28 Apr 2024.

Builds on

214 of 289 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024SocialBench: Sociality Evaluation of Role-Playing Conversational Agents20 Mar
  2. 2024Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent21 Feb
  3. 2024CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation2 Jan
  4. 2023War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars28 Nov
  5. 2023Character-LLM: A Trainable Agent for Role-Playing16 Oct
  6. 2023Humanoid Agents: Platform for Simulating Human-like Generative Agents9 Oct
  7. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View3 Oct
  8. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr

Other references · 206

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2017Proximal Policy Optimization Algorithmscited by 15,215
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  6. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  7. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  8. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  9. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  10. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  11. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  12. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
38 more
  1. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  2. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  4. 2015Continuous control with deep reinforcement learningcited by 3,407
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  6. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  7. 2022Emergent Abilities of Large Language Modelscited by 2,512
  8. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  9. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  10. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  11. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  12. 2020Linformer: Self-Attention with Linear Complexitycited by 1,474
  13. 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,420
  14. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  15. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  16. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
  17. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  18. 2022LaMDA: Language Models for Dialog Applicationscited by 1,220
  19. 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentscited by 1,195
  20. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,190
  21. 2023PaLM 2 Technical Reportcited by 1,162
  22. 2022Ignore Previous Prompt: Attack Techniques For Language Modelscited by 832
  23. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 828
  24. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  25. 2023Large Language Modelscited by 780
  26. 2023Whose Opinions Do Language Models Reflect?cited by 773
  27. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 591
  28. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 556
  29. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  30. 2023Active Retrieval Augmented Generationcited by 516
  31. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Modelscited by 462
  32. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 398
  33. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agentscited by 392
  34. 2022PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Changecited by 382
  35. 2023A Survey on Large Language Models for Recommendationcited by 379
  36. 2023SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agentscited by 367
  37. 2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 360
  38. 2023Chameleon: Plug-and-Play Compositional Reasoning with Large Language Modelscited by 356

50 most cited of 206 All 206 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 38; 2025: 99; 2026: 75.

212 papers.

Sort:

By area:

  1. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 208
  2. 2025Multi-agent Architecture Search via Agentic Supernetcited by 179
  3. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 126
  4. 2024EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithmscited by 113
  5. 2025LLM Social Simulations Are a Promising Research Methodcited by 99
  6. 2025OverThink: Slowdown Attacks on Reasoning LLMscited by 96
  7. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 83
  8. 2024From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agentscited by 82
  9. 2025LLM Generated Persona is a Promise with a Catchcited by 81
  10. 2024PERSONA: A Reproducible Testbed for Pluralistic Alignmentcited by 73
  11. 2025LLM Agents for Education: Advances and Applicationscited by 59
  12. 2025FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoningcited by 58
38 more
  1. 2026Emotion Concepts and their Function in a Large Language Modelcited by 57
  2. 2024Towards Lifelong Dialogue Agents via Timeline-based Memory Managementcited by 51
  3. 2024The Oscars of AI Theater: A Survey on Role-Playing with Language Modelscited by 48
  4. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 44
  5. 2025A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applicationscited by 42
  6. 2024AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarioscited by 40
  7. 2024CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worldscited by 38
  8. 2024On the Structural Memory of LLM Agentscited by 37
  9. 2025The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMscited by 36
  10. 2025Towards Trustworthy GUI Agents: A Surveycited by 34
  11. 2024AI Safety in Generative AI Large Language Models: A Surveycited by 33
  12. 2025Internet of Agents: Fundamentals, Applications, and Challengescited by 31
  13. 2026TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agentscited by 31
  14. 2024LLMs are Biased Teachers: Evaluating LLM Bias in Personalized Educationcited by 28
  15. 2025A Survey of Personalization: From RAG to Agentcited by 27
  16. 2024Emotional RAG: Enhancing Role-Playing Agents through Emotional Retrievalcited by 26
  17. 2024Social Science Meets LLMs: How Reliable Are Large Language Models in Social Simulations?cited by 26
  18. 2025CoSER: A Comprehensive Literary Dataset and Framework for Training and Evaluating LLM Role-Playing and Persona Simulationcited by 26
  19. 2024SweetieChat: A Strategy-Enhanced Role-playing Framework for Diverse Scenarios Handling Emotional Support Agentcited by 24
  20. 2024A Survey on Large Language Model-Based Social Agents in Game-Theoretic Scenarioscited by 23
  21. 2025Emergent Coordination in Multi-Agent Language Modelscited by 23
  22. 2025How Far are LLMs from Being Our Digital Twins? A Benchmark for Persona-Based Behavior Chain Simulationcited by 22
  23. 2025Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMscited by 22
  24. 2024MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agentscited by 21
  25. 2025Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User Personascited by 19
  26. 2025Large language models for artificial general intelligence (AGI): A survey of foundational principles and approachescited by 18
  27. 2026A Survey on LLM-based Conversational User Simulationcited by 18
  28. 2024Capturing Minds, Not Just Words: Enhancing Role-Playing Language Models with Personality-Indicative Datacited by 17
  29. 2025VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcarecited by 17
  30. 2025Evaluating Personalized Tool-Augmented LLMs from the Perspectives of Personalization and Proactivitycited by 17
  31. 2025Security of Internet of Agents: Attacks and Countermeasurescited by 17
  32. 2026MemoryCD: Benchmarking Long-Context User Memory of LLM Agents for Lifelong Cross-Domain Personalizationcited by 17
  33. 2024AutoPatent: A Multi-Agent Framework for Automatic Patent Generationcited by 16
  34. 2025Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compressioncited by 16
  35. 2024ESC-Eval: Evaluating Emotion Support Conversations in Large Language Modelscited by 15
  36. 2024Self-Cognition in Large Language Models: An Exploratory Studycited by 15
  37. 2025Exploring the Impact of Personality Traits on LLM Bias and Toxicitycited by 14
  38. 2025Reasoning Does Not Necessarily Improve Role-Playing Abilitycited by 14

50 most cited of 212 All 212 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Role-Playing Agents Driven by Large Language Models: Current Status, Challenges, and Future Trends
  2. 2024Character is Destiny: Can Role-Playing Language Agents Make Persona-Driven Decisions?
  3. 2024CharacterGPT: A Persona Reconstruction Framework for Role-Playing Agents
  4. 2024Crafting Customisable Characters with LLMs: A Persona-Driven Role-Playing Agent Framework
  5. 2025DPRF: A Generalizable Dynamic Persona Refinement Framework for Optimizing Behavior Alignment Between Personalized LLM Role-Playing Agents and Humans
  6. 2026Deep Persona: A Psychologically Grounded Architecture and Evaluation Framework for Role-Playing Agents and Simulations
  7. 2026Beyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM Agents
  8. 2025Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learning