Toyhom/awesome-computational-character-modeling
Toyhom/awesome-computational-character-modeling has 204 GitHub stars and 4 forks. GitHot measured 0 stars in 24 hours. Last checked 2026-11-18 10:28 UTC. Last push 2026-11-02.
Measured star growth
- in 24h
- 0
- in 7 days
- Collecting history
- in 15 days
- Collecting history
- in 1 month
- Collecting history
Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.
About
Survey companion for Computational Character Modeling: role-playing methods, data foundations, and evaluation, organized by the manuscript.
Developer ToolsREADME.md
Original
Awesome Computational Character Modeling
Role-playing agents through a behavioral science perspective.
A reading list accompanying Computational Character Modeling: A Survey of Role-Playing Agents from a Behavioral Science Perspective.
Explore how character behavior is modeled, what information supports it, and how it is evaluated. The organization follows the survey's chapters and subsections: role modeling → data foundations → evaluation.
Browse the literature directory · Suggest a paper · How to contribute · Download the catalog
143 references · 28 categories
| Survey chapter | Browse |
|---|---|
| III. Behavioral-Science-Informed Role Modeling | Methods |
| IV. Character Information and Data Foundations | Data |
| V. Evaluation of Computational Characters | Evaluation |
Contents
- Behavioral-Science-Informed Role Modeling
- Character Information and Data Foundations
- Evaluation of Computational Characters
Behavioral-Science-Informed Role Modeling
Role Modeling through Behavioral Imitation
Survey §III.A · Edit this category · Detailed list · BibTeX
39 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2026 | Act-Adaptive Margin: Dynamically Calibrating Reward Models for \linebreakSubjective Ambiguity | ACL 2026 | Paper · Code · arXiv |
| 2026 | Character Beyond Speech: Leveraging Role-Playing Evaluation in Audio Large Language Models via Reinforcement Learning | arXiv | Paper |
| 2026 | Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability | arXiv | Paper · Code |
| 2026 | HyCoRA: Hyper-Contrastive Role-Adaptive Learning for Role-Playing | AAAI 2026 | Paper · arXiv |
| 2026 | MOA: Multi-Objective Alignment for Role-Playing Agents | ACL 2026 | Paper · arXiv |
| 2026 | Towards Customized Multimodal Role-Play | arXiv | Paper |
| 2026 | Understanding Generalization in Role-Playing Models via Information Theory | ACL 2026 (Findings) | Paper · arXiv |
| 2026 | VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing | arXiv | Paper |
| 2025 | Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs | ACL 2025 | Paper · arXiv |
| 2025 | BEYOND DIALOGUE: A Profile-Dialogue Alignment Framework Towards General Role-Playing Language Model | ACL 2025 | Paper · Code · arXiv |
| 2025 | CharacterBench: Benchmarking Character Customization of Large Language Models | AAAI 2025 | Paper |
| 2025 | CharacterCraft: Bridging the Literature-Reality Dialogue Gap for Practical Role-Playing Agents | EMNLP 2025 (Findings) | Paper |
| 2025 | CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy Optimization | EMNLP 2025 (Findings) | Paper · arXiv |
| 2025 | MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents | ICLR 2025 | Paper · Code |
| 2025 | OmniCharacter: Towards Immersive Role-Playing Agents with Seamless Speech-Language Personality Interaction | ACL 2025 | Paper · Code · arXiv |
| 2025 | OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas | arXiv | Paper |
| 2025 | ORPP: Self-Optimizing Role-playing Prompts to Enhance Language Model Capabilities | EMNLP 2025 | Paper · arXiv |
| 2025 | RAGs to Riches: RAG-like Few-shot Learning for Large Language Model Role-playing | arXiv | Paper |
| 2025 | RoleRMBench & RoleRM: Towards Reward Modeling for Profile-Based Role Play in Dialogue Systems | arXiv | Paper |
| 2025 | Test-Time-Matching: Decouple Personality, Memory, and Linguistic Style in LLM-based Role-Playing Language Agent | arXiv | Paper |
| 2025 | The Rise of Darkness: Safety-Utility Trade-Offs in Role-Playing Dialogue Agents | ACL 2025 (Findings) | Paper · arXiv |
| 2024 | A Multi-Task Role-Playing Agent Capable of Imitating Character Linguistic Styles | arXiv | Paper |
| 2024 | CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models | EMNLP 2024 (Industry) | Paper · arXiv |
| 2024 | Enhancing Role-playing Systems through Aggressive Queries: Evaluation and Improvement | arXiv | Paper |
| 2024 | ERABAL: Enhancing Role-Playing Agents through Boundary-Aware Learning | arXiv | Paper |
| 2024 | Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment | ACL 2024 | Paper · Code · arXiv |
| 2024 | MINDECHO: Role-Playing Language Agents for Key Opinion Leaders | arXiv | Paper |
| 2024 | Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent | EMNLP 2024 | Paper · Code · arXiv |
| 2024 | Role-playing Prompt Framework: Generation and Evaluation | arXiv | Paper |
| 2024 | RoleCraft-GLM: Advancing Personalized Role-Playing in Large Language Models | PERSONALIZE 2024 (Workshop) | Paper |
| 2024 | RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models | ACL 2024 (Findings) | Paper · arXiv |
| 2023 | ChatHaruhi: Reviving Anime Character in Reality via Large Language Model | arXiv | Paper · Code |
| 2023 | Direct Preference Optimization: Your Language Model is Secretly a Reward Model | NeurIPS 2023 | Paper |
| 2023 | Thespian: Multi-Character Text Role-Playing Game Agents | arXiv | Paper |
| 2022 | Finetuned Language Models Are Zero-Shot Learners | ICLR 2022 | Paper |
| 2022 | LoRA: Low-Rank Adaptation of Large Language Models | ICLR 2022 | Paper · Code |
| 2022 | Training language models to follow instructions with human feedback | NeurIPS 2022 | Paper |
| 2020 | Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks | NeurIPS 2020 | Paper |
| 1913 | Psychology as the Behaviorist Views It | Psychol. Rev. | Paper |
Role Modeling through Internal Cognitive States
Survey §III.B · Edit this category · Detailed list · BibTeX
35 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2026 | ActorMind: Emulating Human Actor Reasoning for Speech Role-Playing | ACL 2026 (Findings) | Paper · arXiv |
| 2026 | BOOKMARKS: Efficient Active Storyline Memory for Role-playing | arXiv | Paper |
| 2026 | Character-R1: Enhancing Role-Aware Reasoning in Role-Playing Agents via RLVR | arXiv | Paper |
| 2026 | CRPO: Character-centric Group Relative Policy Optimization for Role-aware Reasoning in Role-playing Agents | arXiv | Paper |
| 2026 | DeSRPA: Decoupled Speech Role-Playing Agent via Inference-Time Intervention | arXiv | Paper |
| 2026 | Enhancing Persona Following at Decoding Time via Dynamic Importance Estimation for Role-Playing Agents | arXiv | Paper |
| 2026 | HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing | ACL 2026 (Findings) | Paper · arXiv |
| 2026 | Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization | arXiv | Paper |
| 2026 | Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLMs | ACL 2026 (Findings) | Paper · arXiv |
| 2026 | PsyMem: Fine-grained psychological alignment and Explicit Memory Control for Advanced Role-Playing LLMs | TACL | Paper · arXiv |
| 2026 | Reward-Decomposed Reinforcement Learning for Immersive Video Role-Playing | arXiv | Paper |
| 2026 | Staying In Character: Perspective-Bounded Memory For Book-Based Role-Playing Agents | arXiv | Paper |
| 2026 | Through the Lens of Character: Resolving Modality-Role Interference in Multimodal Role-Playing Agent | arXiv | Paper |
| 2025 | Beyond One World: Benchmarking Super Heros in Role-Playing Across Multiversal Contexts | arXiv | Paper |
| 2025 | Beyond Profile: From Surface-Level Facts to Deep Persona Simulation in LLMs | ACL 2025 (Findings) | Paper · arXiv |
| 2025 | CoSER: Coordinating LLM-Based Persona Simulation of Established Roles | ICML 2025 | Paper |
| 2025 | Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learning | ACL 2025 (Findings) | Paper · arXiv |
| 2025 | Guess What I am Thinking: A Benchmark for Inner Thought Reasoning of Role-Playing Language Agents | EMNLP 2025 (Findings) | Paper · Code · arXiv |
| 2025 | MOOM: Maintenance, Organization and Optimization of Memory in Ultra-Long Role-Playing Dialogues | arXiv | Paper |
| 2025 | R-CHAR: A Metacognition-Driven Framework for Role-Playing in Large Language Models | EMNLP 2025 | Paper |
| 2025 | RAIDEN-R1: Improving Role-awareness of LLMs via GRPO with Verifiable Reward | arXiv | Paper |
| 2025 | Reasoning Does Not Necessarily Improve Role-Playing Ability | ACL 2025 (Findings) | Paper · arXiv |
| 2025 | Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-Playing | EMNLP 2025 | Paper · arXiv |
| 2025 | SHARP: Unlocking Interactive Hallucination via Stance Transfer in Role-Playing LLMs | ACL 2025 (Findings) | Paper · arXiv |
| 2025 | Tell Me What You Don't Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing | ACL 2025 (Findings) | Paper · arXiv |
| 2025 | Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning | arXiv | Paper |
| 2024 | Mitigating Hallucination in Fictional Character Role-Play | EMNLP 2024 (Findings) | Paper · Code · arXiv |
| 2024 | RoleAgent: Building, Interacting, and Benchmarking High-quality Role-Playing Agents from Scripts | NeurIPS 2024 | Paper |
| 2024 | Thinking Before Speaking: A Role-playing Model with Mindset | arXiv | Paper |
| 2023 | ReAct: Synergizing Reasoning and Acting in Language Models | ICLR 2023 | Paper |
| 2022 | Chain-of-Thought Prompting Elicits Reasoning in Large Language Models | NeurIPS 2022 | Paper |
| 2022 | STaR: Bootstrapping Reasoning With Reasoning | NeurIPS 2022 | Paper |
| 2020 | Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks | NeurIPS 2020 | Paper |
| 1978 | Does the chimpanzee have a theory of mind? | Behav. Brain Sci. | Paper |
| 1948 | Cognitive Maps in Rats and Men | Psychol. Rev. | Paper |
Role Modeling through Experience and Explicit Rules
Survey §III.C · Edit this category · Detailed list · BibTeX
13 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2026 | Codified Finite-state Machines for Role-playing | arXiv | Paper |
| 2026 | Deriving Character Logic from Storyline as Codified Decision Trees | ACL 2026 | Paper · arXiv |
| 2026 | From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents | arXiv | Paper · Code |
| 2026 | RPA-Check: A Multi-Stage Automated Framework for Evaluating Dynamic LLM-based Role-Playing Agents | arXiv | Paper |
| 2025 | Codifying Character Logic in Role-Playing | arXiv | Paper |
| 2025 | Identity-Driven Hierarchical Role-Playing Agents | NLPCC 2025 | Paper · arXiv |
| 2025 | Operation Veja: Fixing Fundamental Concepts Missing from Modern Roleplaying Training Paradigms | arXiv | Paper · Code |
| 2024 | Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works | EMNLP 2024 | Paper · Code · arXiv |
| 2024 | Quantifying and Optimizing Global Faithfulness in Persona-driven Role-playing | NeurIPS 2024 | Paper |
| 2023 | Character-LLM: A Trainable Agent for Role-Playing | EMNLP 2023 | Paper |
| 2022 | Constitutional AI: Harmlessness from AI Feedback | arXiv | Paper |
| 2001 | The Psychology of Life Stories | Rev. Gen. Psychol. | Paper |
| 1979 | Role Theory: Expectations, Identities, and Behaviors | Academic Press | Paper |
Role Modeling through Situated Interaction
Survey §III.D · Edit this category · Detailed list · BibTeX
17 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2026 | AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-Playing | ACL 2026 (Findings) | Paper · arXiv |
| 2026 | DynSess: Dynamic Session-Level Evaluation and Optimization Framework for Role-Playing Agents | arXiv | Paper |
| 2026 | PersonaArena: Dynamic Simulation for Evaluating and Enhancing Persona-Level Role-Playing in Large Language Models | ACL 2026 (Findings) | Paper · arXiv |
| 2025 | CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds | NAACL 2025 | Paper · arXiv |
| 2025 | RolePlot: A Systematic Framework for Evaluating and Enhancing the Plot-Progression Capabilities of Role-Playing Agents | ACL 2025 | Paper |
| 2025 | Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents | EMNLP 2025 | Paper · arXiv |
| 2024 | PingPong: A Benchmark for Role-Playing Language Models with User Emulation and Multi-Model Evaluation | arXiv | Paper |
| 2024 | SocialBench: Sociality Evaluation of Role-Playing Conversational Agents | ACL 2024 (Findings) | Paper · Code · arXiv |
| 2024 | SOTOPIA-$\pi$: Interactive Learning of Socially Intelligent Language Agents | ACL 2024 | Paper · arXiv |
| 2024 | SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents | ICLR 2024 | Paper |
| 2024 | TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models | ACL 2024 (Findings) | Paper · arXiv |
| 2023 | CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society | NeurIPS 2023 | Paper · Code |
| 2023 | Generative Agents: Interactive Simulacra of Human Behavior | UIST 2023 | Paper · arXiv |
| 2023 | Lyfe Agents: Generative agents for low-cost real-time social interactions | arXiv | Paper |
| 1987 | Plans and Situated Actions | Cambridge University Press | Paper |
| 1959 | The Presentation of Self in Everyday Life | Doubleday | Paper |
| 1934 | Mind, Self, and Society | University of Chicago Press | Paper |
Role Modeling through Personality and Value Traits
Survey §III.E · Edit this category · Detailed list · BibTeX
18 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2026 | Facet-Level Persona Control by Trait-Activated Routing with Contrastive SAE for Role-Playing LLMs | PAKDD 2026 | Paper · Code · arXiv |
| 2026 | Identifying and Mitigating Bottlenecks in Role-Playing Agents: A Systematic Study of Disentangling Character Profile Axes | arXiv | Paper |
| 2026 | MERRY: Semantically Decoupled Evaluation of Multimodal Emotional and Role Consistencies of Role-Playing Agents | arXiv | Paper |
| 2026 | RoleCDE:Benchmarking and Mitigating Role-Alignment Trade-offs in Role-Playing Agents | ACL 2026 (Findings) | Paper · Code · arXiv |
| 2026 | Too Good to be Bad: On the Failure of LLMs to Role-Play Villains | ACL 2026 (Findings) | Paper · arXiv |
| 2026 | Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models | ACL 2026 | Paper · arXiv |
| 2025 | Enhancing Character-Coherent Role-Playing Dialogue with a Verifiable Emotion Reward | Information | Paper |
| 2025 | PsyPlay: Personality-Infused Role-Playing Conversational Agents | arXiv | Paper |
| 2025 | RVBench: Role values benchmark for role-playing LLMs | CHBAH | Paper |
| 2024 | Capturing Minds, Not Just Words: Enhancing Role-Playing Language Models with Personality-Indicative Data | EMNLP 2024 (Findings) | Paper · Code · arXiv |
| 2024 | Character is Destiny: Can Role-Playing Language Agents Make Persona-Driven Decisions? | arXiv | Paper |
| 2024 | InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews | ACL 2024 | Paper · arXiv |
| 2024 | Role-Play Paradox in Large Language Models: Reasoning Performance Gains and Ethical Dilemmas | arXiv | Paper |
| 2023 | Building Persona Consistent Dialogue Agents with Offline Reinforcement Learning | EMNLP 2023 | Paper · arXiv |
| 2023 | CharacterChat: Learning towards Conversational AI with Personalized Social Support | arXiv | Paper · Code |
| 2023 | Do LLMs Possess a Personality? Making the MBTI Test an Amazing Evaluation for Large Language Models | arXiv | Paper · Code |
| 1994 | The Role of Emotion in Believable Agents | CACM | Paper |
| 1992 | Universals in the Content and Structure of Values | Adv. Exp. Soc. Psychol. | Paper |
Comparative Synthesis
Survey §III.F · Edit this category · Detailed list · BibTeX
A comparison of the five modeling approaches and the character properties they aim to control.
Character Information and Data Foundations
Character Sources
Survey §IV.A · Edit this category · Detailed list · BibTeX
10 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2026 | PersonaArena: Dynamic Simulation for Evaluating and Enhancing Persona-Level Role-Playing in Large Language Models | ACL 2026 (Findings) | Paper · arXiv |
| 2026 | RoleCDE:Benchmarking and Mitigating Role-Alignment Trade-offs in Role-Playing Agents | ACL 2026 (Findings) | Paper · Code · arXiv |
| 2025 | AudioRole: An Audio Dataset for Character Role-Playing in Large Language Models | arXiv | Paper |
| 2025 | BEYOND DIALOGUE: A Profile-Dialogue Alignment Framework Towards General Role-Playing Language Model | ACL 2025 | Paper · Code · arXiv |
| 2025 | CoSER: Coordinating LLM-Based Persona Simulation of Established Roles | ICML 2025 | Paper |
| 2025 | OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas | arXiv | Paper |
| 2024 | BaiJia: A Large-Scale Role-Playing Agent Corpus of Chinese Historical Characters | arXiv | Paper |
| 2024 | CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models | EMNLP 2024 (Industry) | Paper · arXiv |
| 2024 | How Well Can LLMs Echo Us? Evaluating AI Chatbots' Role-Play Ability with ECHO | arXiv | Paper · Code |
| 2024 | RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models | ACL 2024 (Findings) | Paper · arXiv |
Role Information and Data Modalities
Survey §IV.B · Edit this category · Detailed list · BibTeX
10 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2026 | AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-Playing | ACL 2026 (Findings) | Paper · arXiv |
| 2026 | From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents | arXiv | Paper · Code |
| 2026 | PsyMem: Fine-grained psychological alignment and Explicit Memory Control for Advanced Role-Playing LLMs | TACL | Paper · arXiv |
| 2026 | Reward-Decomposed Reinforcement Learning for Immersive Video Role-Playing | arXiv | Paper |
| 2025 | AudioRole: An Audio Dataset for Character Role-Playing in Large Language Models | arXiv | Paper |
| 2025 | CoSER: Coordinating LLM-Based Persona Simulation of Established Roles | ICML 2025 | Paper |
| 2025 | MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents | ICLR 2025 | Paper · Code |
| 2025 | OmniCharacter: Towards Immersive Role-Playing Agents with Seamless Speech-Language Personality Interaction | ACL 2025 | Paper · Code · arXiv |
| 2025 | RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following | ACL 2025 (Findings) | Paper · Code · arXiv |
| 2024 | Capturing Minds, Not Just Words: Enhancing Role-Playing Language Models with Personality-Indicative Data | EMNLP 2024 (Findings) | Paper · Code · arXiv |
Data Construction and Quality Control
Survey §IV.C · Edit this category · Detailed list · BibTeX
14 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2026 | AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-Playing | ACL 2026 (Findings) | Paper · arXiv |
| 2026 | From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents | arXiv | Paper · Code |
| 2026 | MERRY: Semantically Decoupled Evaluation of Multimodal Emotional and Role Consistencies of Role-Playing Agents | arXiv | Paper |
| 2026 | RoleCDE:Benchmarking and Mitigating Role-Alignment Trade-offs in Role-Playing Agents | ACL 2026 (Findings) | Paper · Code · arXiv |
| 2025 | AudioRole: An Audio Dataset for Character Role-Playing in Large Language Models | arXiv | Paper |
| 2025 | CharacterBench: Benchmarking Character Customization of Large Language Models | AAAI 2025 | Paper |
| 2025 | CoSER: Coordinating LLM-Based Persona Simulation of Established Roles | ICML 2025 | Paper |
| 2025 | OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas | arXiv | Paper |
| 2025 | RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following | ACL 2025 (Findings) | Paper · Code · arXiv |
| 2024 | RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models | ACL 2024 (Findings) | Paper · arXiv |
| 2023 | Direct Preference Optimization: Your Language Model is Secretly a Reward Model | NeurIPS 2023 | Paper |
| 2023 | Self-Instruct: Aligning Language Models with Self-Generated Instructions | ACL 2023 | Paper · Code · arXiv |
| 2022 | Finetuned Language Models Are Zero-Shot Learners | ICLR 2022 | Paper |
| 2022 | Training language models to follow instructions with human feedback | NeurIPS 2022 | Paper |
Scale and Coverage
Survey §IV.D · Edit this category · Detailed list · BibTeX
55 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2026 | Act-Adaptive Margin: Dynamically Calibrating Reward Models for \linebreakSubjective Ambiguity | ACL 2026 | Paper · Code · arXiv |
| 2026 | AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-Playing | ACL 2026 (Findings) | Paper · arXiv |
| 2026 | Character Beyond Speech: Leveraging Role-Playing Evaluation in Audio Large Language Models via Reinforcement Learning | arXiv | Paper |
| 2026 | Deriving Character Logic from Storyline as Codified Decision Trees | ACL 2026 | Paper · arXiv |
| 2026 | DynSess: Dynamic Session-Level Evaluation and Optimization Framework for Role-Playing Agents | arXiv | Paper |
| 2026 | Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability | arXiv | Paper · Code |
| 2026 | From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents | arXiv | Paper · Code |
| 2026 | Identifying and Mitigating Bottlenecks in Role-Playing Agents: A Systematic Study of Disentangling Character Profile Axes | arXiv | Paper |
| 2026 | MERRY: Semantically Decoupled Evaluation of Multimodal Emotional and Role Consistencies of Role-Playing Agents | arXiv | Paper |
| 2026 | OmniCharacter++: Towards Comprehensive Benchmark for Realistic Role-Playing Agents | TPAMI | Paper · Code |
| 2026 | PersonaArena: Dynamic Simulation for Evaluating and Enhancing Persona-Level Role-Playing in Large Language Models | ACL 2026 (Findings) | Paper · arXiv |
| 2026 | PsyMem: Fine-grained psychological alignment and Explicit Memory Control for Advanced Role-Playing LLMs | TACL | Paper · arXiv |
| 2026 | Reward-Decomposed Reinforcement Learning for Immersive Video Role-Playing | arXiv | Paper |
| 2026 | Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models | ACL 2026 | Paper · arXiv |
| 2026 | Towards Customized Multimodal Role-Play | arXiv | Paper |
| 2026 | Understanding Generalization in Role-Playing Models via Information Theory | ACL 2026 (Findings) | Paper · arXiv |
| 2025 | AudioRole: An Audio Dataset for Character Role-Playing in Large Language Models | arXiv | Paper |
| 2025 | BEYOND DIALOGUE: A Profile-Dialogue Alignment Framework Towards General Role-Playing Language Model | ACL 2025 | Paper · Code · arXiv |
| 2025 | Beyond Profile: From Surface-Level Facts to Deep Persona Simulation in LLMs | ACL 2025 (Findings) | Paper · arXiv |
| 2025 | CharacterBench: Benchmarking Character Customization of Large Language Models | AAAI 2025 | Paper |
| 2025 | CharacterCraft: Bridging the Literature-Reality Dialogue Gap for Practical Role-Playing Agents | EMNLP 2025 (Findings) | Paper |
| 2025 | Codifying Character Logic in Role-Playing | arXiv | Paper |
| 2025 | CoSER: Coordinating LLM-Based Persona Simulation of Established Roles | ICML 2025 | Paper |
| 2025 | CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy Optimization | EMNLP 2025 (Findings) | Paper · arXiv |
| 2025 | Enhancing Character-Coherent Role-Playing Dialogue with a Verifiable Emotion Reward | Information | Paper |
| 2025 | Identity-Driven Hierarchical Role-Playing Agents | NLPCC 2025 | Paper · arXiv |
| 2025 | MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents | ICLR 2025 | Paper · Code |
| 2025 | MOOM: Maintenance, Organization and Optimization of Memory in Ultra-Long Role-Playing Dialogues | arXiv | Paper |
| 2025 | OmniCharacter: Towards Immersive Role-Playing Agents with Seamless Speech-Language Personality Interaction | ACL 2025 | Paper · Code · arXiv |
| 2025 | OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas | arXiv | Paper |
| 2025 | Operation Veja: Fixing Fundamental Concepts Missing from Modern Roleplaying Training Paradigms | arXiv | Paper · Code |
| 2025 | PsyPlay: Personality-Infused Role-Playing Conversational Agents | arXiv | Paper |
| 2025 | RAGs to Riches: RAG-like Few-shot Learning for Large Language Model Role-playing | arXiv | Paper |
| 2025 | RolePlot: A Systematic Framework for Evaluating and Enhancing the Plot-Progression Capabilities of Role-Playing Agents | ACL 2025 | Paper |
| 2025 | RoleRMBench & RoleRM: Towards Reward Modeling for Profile-Based Role Play in Dialogue Systems | arXiv | Paper |
| 2025 | Tell Me What You Don't Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing | ACL 2025 (Findings) | Paper · arXiv |
| 2025 | Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents | EMNLP 2025 | Paper · arXiv |
| 2025 | VoxRole: A Comprehensive Benchmark for Evaluating Speech-Based Role-Playing Agents | arXiv | Paper |
| 2024 | A Multi-Task Role-Playing Agent Capable of Imitating Character Linguistic Styles | arXiv | Paper |
| 2024 | BaiJia: A Large-Scale Role-Playing Agent Corpus of Chinese Historical Characters | arXiv | Paper |
| 2024 | Character is Destiny: Can Role-Playing Language Agents Make Persona-Driven Decisions? | arXiv | Paper |
| 2024 | CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models | EMNLP 2024 (Industry) | Paper · arXiv |
| 2024 | Enhancing Role-playing Systems through Aggressive Queries: Evaluation and Improvement | arXiv | Paper |
| 2024 | ERABAL: Enhancing Role-Playing Agents through Boundary-Aware Learning | arXiv | Paper |
| 2024 | Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works | EMNLP 2024 | Paper · Code · arXiv |
| 2024 | Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment | ACL 2024 | Paper · Code · arXiv |
| 2024 | MINDECHO: Role-Playing Language Agents for Key Opinion Leaders | arXiv | Paper |
| 2024 | Mitigating Hallucination in Fictional Character Role-Play | EMNLP 2024 (Findings) | Paper · Code · arXiv |
| 2024 | Quantifying and Optimizing Global Faithfulness in Persona-driven Role-playing | NeurIPS 2024 | Paper |
| 2024 | Role-playing Prompt Framework: Generation and Evaluation | arXiv | Paper |
| 2024 | RoleCraft-GLM: Advancing Personalized Role-Playing in Large Language Models | PERSONALIZE 2024 (Workshop) | Paper |
| 2024 | RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models | ACL 2024 (Findings) | Paper · arXiv |
| 2024 | Thinking Before Speaking: A Role-playing Model with Mindset | arXiv | Paper |
| 2023 | Character-LLM: A Trainable Agent for Role-Playing | EMNLP 2023 | Paper |
| 2023 | ChatHaruhi: Reviving Anime Character in Reality via Large Language Model | arXiv | Paper · Code |
Data Affordances and Modeling Limits
Survey §IV.E · Edit this category · Detailed list · BibTeX
9 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2026 | AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-Playing | ACL 2026 (Findings) | Paper · arXiv |
| 2026 | From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents | arXiv | Paper · Code |
| 2026 | PsyMem: Fine-grained psychological alignment and Explicit Memory Control for Advanced Role-Playing LLMs | TACL | Paper · arXiv |
| 2026 | RoleCDE:Benchmarking and Mitigating Role-Alignment Trade-offs in Role-Playing Agents | ACL 2026 (Findings) | Paper · Code · arXiv |
| 2025 | CoSER: Coordinating LLM-Based Persona Simulation of Established Roles | ICML 2025 | Paper |
| 2025 | RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following | ACL 2025 (Findings) | Paper · Code · arXiv |
| 2024 | BaiJia: A Large-Scale Role-Playing Agent Corpus of Chinese Historical Characters | arXiv | Paper |
| 2024 | Capturing Minds, Not Just Words: Enhancing Role-Playing Language Models with Personality-Indicative Data | EMNLP 2024 (Findings) | Paper · Code · arXiv |
| 2024 | RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models | ACL 2024 (Findings) | Paper · arXiv |
Evaluation of Computational Characters
Evaluation Targets
Knowledge and expression
E1: character identity, knowledge, and information boundaries
Survey §V.A / E1 · Edit this category · Detailed list · BibTeX
3 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2026 | Staying In Character: Perspective-Bounded Memory For Book-Based Role-Playing Agents | arXiv | Paper |
| 2024 | TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models | ACL 2024 (Findings) | Paper · arXiv |
| 2023 | RoleEval: A Bilingual Role Evaluation Benchmark for Large Language Models | arXiv | Paper |
E2: linguistic style, voice, and multimodal expression
Survey §V.A / E2 · Edit this category · Detailed list · BibTeX
3 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2025 | Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents | EMNLP 2025 | Paper · arXiv |
| 2025 | VoxRole: A Comprehensive Benchmark for Evaluating Speech-Based Role-Playing Agents | arXiv | Paper |
| 2024 | RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models | ACL 2024 (Findings) | Paper · arXiv |
Dispositions and internal processes
E3: personality, values, and emotion
Survey §V.A / E3 · Edit this category · Detailed list · BibTeX
3 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2025 | CharacterBench: Benchmarking Character Customization of Large Language Models | AAAI 2025 | Paper |
| 2025 | Moral Susceptibility and Robustness under Persona Role-Play in Large Language Models | arXiv | Paper |
| 2024 | InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews | ACL 2024 | Paper · arXiv |
E4: reasoning, intention, and internal state
Survey §V.A / E4 · Edit this category · Detailed list · BibTeX
3 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2025 | Beyond One World: Benchmarking Super Heros in Role-Playing Across Multiversal Contexts | arXiv | Paper |
| 2025 | Guess What I am Thinking: A Benchmark for Inner Thought Reasoning of Role-Playing Language Agents | EMNLP 2025 (Findings) | Paper · Code · arXiv |
| 2024 | Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works | EMNLP 2024 | Paper · Code · arXiv |
Temporal, social, and strategic behavior
E5: memory, longitudinal consistency, and character change
Survey §V.A / E5 · Edit this category · Detailed list · BibTeX
3 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2026 | DynSess: Dynamic Session-Level Evaluation and Optimization Framework for Role-Playing Agents | arXiv | Paper |
| 2026 | From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents | arXiv | Paper · Code |
| 2024 | TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models | ACL 2024 (Findings) | Paper · arXiv |
E6: relationships, multi-character behavior, and social interaction
Survey §V.A / E6 · Edit this category · Detailed list · BibTeX
3 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2025 | CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds | NAACL 2025 | Paper · arXiv |
| 2025 | DEBATE: A Large-Scale Benchmark for Evaluating Opinion Dynamics in Role-Playing LLM Agents | arXiv | Paper |
| 2024 | SocialBench: Sociality Evaluation of Role-Playing Conversational Agents | ACL 2024 (Findings) | Paper · Code · arXiv |
E7: situated action, strategy, and plot progression
Survey §V.A / E7 · Edit this category · Detailed list · BibTeX
4 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2026 | BOOKMARKS: Efficient Active Storyline Memory for Role-playing | arXiv | Paper |
| 2025 | RolePlot: A Systematic Framework for Evaluating and Enhancing the Plot-Progression Capabilities of Role-Playing Agents | ACL 2025 | Paper |
| 2024 | Character is Destiny: Can Role-Playing Language Agents Make Persona-Driven Decisions? | arXiv | Paper |
| 2024 | On the Decision-Making Abilities in Role-Playing using Large Language Models | arXiv | Paper |
Safety and user experience
E8: safety, refusal, and role boundaries
Survey §V.A / E8 · Edit this category · Detailed list · BibTeX
2 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2026 | Too Good to be Bad: On the Failure of LLMs to Role-Play Villains | ACL 2026 (Findings) | Paper · arXiv |
| 2025 | Tell Me What You Don't Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing | ACL 2025 (Findings) | Paper · arXiv |
E9: naturalness, credibility, immersion, and user experience
Survey §V.A / E9 · Edit this category · Detailed list · BibTeX
2 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2024 | CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation | ACL 2024 | Paper · Code · arXiv |
| 2024 | How Well Can LLMs Echo Us? Evaluating AI Chatbots' Role-Play Ability with ECHO | arXiv | Paper · Code |
Test Settings
Character source
Survey §V.B · Edit this category · Detailed list · BibTeX
5 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2026 | From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents | arXiv | Paper · Code |
| 2026 | Rethinking Role-Playing Evaluation: Anonymous Benchmarking and a Systematic Study of Personality Effects | arXiv | Paper |
| 2025 | DEBATE: A Large-Scale Benchmark for Evaluating Opinion Dynamics in Role-Playing LLM Agents | arXiv | Paper |
| 2024 | InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews | ACL 2024 | Paper · arXiv |
| 2023 | RoleEval: A Bilingual Role Evaluation Benchmark for Large Language Models | arXiv | Paper |
Time and participants
Survey §V.B · Edit this category · Detailed list · BibTeX
4 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2025 | CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds | NAACL 2025 | Paper · arXiv |
| 2025 | DEBATE: A Large-Scale Benchmark for Evaluating Opinion Dynamics in Role-Playing LLM Agents | arXiv | Paper |
| 2025 | FURINA: A Fully Customizable Role-Playing Benchmark via Scalable Multi-Agent Collaboration Pipeline | arXiv | Paper |
| 2024 | CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation | ACL 2024 | Paper · Code · arXiv |
Scenario and response format
Survey §V.B · Edit this category · Detailed list · BibTeX
2 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2025 | RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following | ACL 2025 (Findings) | Paper · Code · arXiv |
| 2024 | SocialBench: Sociality Evaluation of Role-Playing Conversational Agents | ACL 2024 (Findings) | Paper · Code · arXiv |
Observed benchmark distribution
Survey §V.B · Edit this category · Detailed list · BibTeX
75 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2026 | Act-Adaptive Margin: Dynamically Calibrating Reward Models for \linebreakSubjective Ambiguity | ACL 2026 | Paper · Code · arXiv |
| 2026 | ActorMind: Emulating Human Actor Reasoning for Speech Role-Playing | ACL 2026 (Findings) | Paper · arXiv |
| 2026 | AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-Playing | ACL 2026 (Findings) | Paper · arXiv |
| 2026 | ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time? | arXiv | Paper |
| 2026 | BOOKMARKS: Efficient Active Storyline Memory for Role-playing | arXiv | Paper |
| 2026 | Character Beyond Speech: Leveraging Role-Playing Evaluation in Audio Large Language Models via Reinforcement Learning | arXiv | Paper |
| 2026 | Deriving Character Logic from Storyline as Codified Decision Trees | ACL 2026 | Paper · arXiv |
| 2026 | DynSess: Dynamic Session-Level Evaluation and Optimization Framework for Role-Playing Agents | arXiv | Paper |
| 2026 | Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLMs | ACL 2026 (Findings) | Paper · arXiv |
| 2026 | MERRY: Semantically Decoupled Evaluation of Multimodal Emotional and Role Consistencies of Role-Playing Agents | arXiv | Paper |
| 2026 | OmniCharacter++: Towards Comprehensive Benchmark for Realistic Role-Playing Agents | TPAMI | Paper · Code |
| 2026 | PersonaArena: Dynamic Simulation for Evaluating and Enhancing Persona-Level Role-Playing in Large Language Models | ACL 2026 (Findings) | Paper · arXiv |
| 2026 | PsyMem: Fine-grained psychological alignment and Explicit Memory Control for Advanced Role-Playing LLMs | TACL | Paper · arXiv |
| 2026 | Rethinking Role-Playing Evaluation: Anonymous Benchmarking and a Systematic Study of Personality Effects | arXiv | Paper |
| 2026 | Reward-Decomposed Reinforcement Learning for Immersive Video Role-Playing | arXiv | Paper |
| 2026 | RoleCDE:Benchmarking and Mitigating Role-Alignment Trade-offs in Role-Playing Agents | ACL 2026 (Findings) | Paper · Code · arXiv |
| 2026 | RPA-Check: A Multi-Stage Automated Framework for Evaluating Dynamic LLM-based Role-Playing Agents | arXiv | Paper |
| 2026 | Staying In Character: Perspective-Bounded Memory For Book-Based Role-Playing Agents | arXiv | Paper |
| 2026 | Too Good to be Bad: On the Failure of LLMs to Role-Play Villains | ACL 2026 (Findings) | Paper · arXiv |
| 2026 | Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models | ACL 2026 | Paper · arXiv |
| 2026 | Towards Customized Multimodal Role-Play | arXiv | Paper |
| 2026 | Understanding Generalization in Role-Playing Models via Information Theory | ACL 2026 (Findings) | Paper · arXiv |
| 2025 | AudioRole: An Audio Dataset for Character Role-Playing in Large Language Models | arXiv | Paper |
| 2025 | BEYOND DIALOGUE: A Profile-Dialogue Alignment Framework Towards General Role-Playing Language Model | ACL 2025 | Paper · Code · arXiv |
| 2025 | Beyond One World: Benchmarking Super Heros in Role-Playing Across Multiversal Contexts | arXiv | Paper |
| 2025 | Beyond Profile: From Surface-Level Facts to Deep Persona Simulation in LLMs | ACL 2025 (Findings) | Paper · arXiv |
| 2025 | CharacterBench: Benchmarking Character Customization of Large Language Models | AAAI 2025 | Paper |
| 2025 | CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds | NAACL 2025 | Paper · arXiv |
| 2025 | CharacterCraft: Bridging the Literature-Reality Dialogue Gap for Practical Role-Playing Agents | EMNLP 2025 (Findings) | Paper |
| 2025 | Codifying Character Logic in Role-Playing | arXiv | Paper |
| 2025 | CoSER: Coordinating LLM-Based Persona Simulation of Established Roles | ICML 2025 | Paper |
| 2025 | CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy Optimization | EMNLP 2025 (Findings) | Paper · arXiv |
| 2025 | DEBATE: A Large-Scale Benchmark for Evaluating Opinion Dynamics in Role-Playing LLM Agents | arXiv | Paper |
| 2025 | FURINA: A Fully Customizable Role-Playing Benchmark via Scalable Multi-Agent Collaboration Pipeline | arXiv | Paper |
| 2025 | Guess What I am Thinking: A Benchmark for Inner Thought Reasoning of Role-Playing Language Agents | EMNLP 2025 (Findings) | Paper · Code · arXiv |
| 2025 | Identity-Driven Hierarchical Role-Playing Agents | NLPCC 2025 | Paper · arXiv |
| 2025 | MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents | ICLR 2025 | Paper · Code |
| 2025 | MOOM: Maintenance, Organization and Optimization of Memory in Ultra-Long Role-Playing Dialogues | arXiv | Paper |
| 2025 | Moral Susceptibility and Robustness under Persona Role-Play in Large Language Models | arXiv | Paper |
| 2025 | OmniCharacter: Towards Immersive Role-Playing Agents with Seamless Speech-Language Personality Interaction | ACL 2025 | Paper · Code · arXiv |
| 2025 | OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas | arXiv | Paper |
| 2025 | PsyPlay: Personality-Infused Role-Playing Conversational Agents | arXiv | Paper |
| 2025 | RAGs to Riches: RAG-like Few-shot Learning for Large Language Model Role-playing | arXiv | Paper |
| 2025 | Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-Playing | EMNLP 2025 | Paper · arXiv |
| 2025 | RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing | EMNLP 2025 (Findings) | Paper · arXiv |
| 2025 | Role-Playing Evaluation for Large Language Models | MIS4TEL 2025 | Paper · Code · arXiv |
| 2025 | RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following | ACL 2025 (Findings) | Paper · Code · arXiv |
| 2025 | RolePlot: A Systematic Framework for Evaluating and Enhancing the Plot-Progression Capabilities of Role-Playing Agents | ACL 2025 | Paper |
| 2025 | RoleRMBench & RoleRM: Towards Reward Modeling for Profile-Based Role Play in Dialogue Systems | arXiv | Paper |
| 2025 | RVBench: Role values benchmark for role-playing LLMs | CHBAH | Paper |
| 2025 | SHARP: Unlocking Interactive Hallucination via Stance Transfer in Role-Playing LLMs | ACL 2025 (Findings) | Paper · arXiv |
| 2025 | Tell Me What You Don't Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing | ACL 2025 (Findings) | Paper · arXiv |
| 2025 | Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents | EMNLP 2025 | Paper · arXiv |
| 2025 | VoxRole: A Comprehensive Benchmark for Evaluating Speech-Based Role-Playing Agents | arXiv | Paper |
| 2024 | A Multi-Task Role-Playing Agent Capable of Imitating Character Linguistic Styles | arXiv | Paper |
| 2024 | BaiJia: A Large-Scale Role-Playing Agent Corpus of Chinese Historical Characters | arXiv | Paper |
| 2024 | Character is Destiny: Can Role-Playing Language Agents Make Persona-Driven Decisions? | arXiv | Paper |
| 2024 | CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation | ACL 2024 | Paper · Code · arXiv |
| 2024 | Enhancing Role-playing Systems through Aggressive Queries: Evaluation and Improvement | arXiv | Paper |
| 2024 | ERABAL: Enhancing Role-Playing Agents through Boundary-Aware Learning | arXiv | Paper |
| 2024 | Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works | EMNLP 2024 | Paper · Code · arXiv |
| 2024 | How Well Can LLMs Echo Us? Evaluating AI Chatbots' Role-Play Ability with ECHO | arXiv | Paper · Code |
| 2024 | InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews | ACL 2024 | Paper · arXiv |
| 2024 | Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment | ACL 2024 | Paper · Code · arXiv |
| 2024 | MINDECHO: Role-Playing Language Agents for Key Opinion Leaders | arXiv | Paper |
| 2024 | Mitigating Hallucination in Fictional Character Role-Play | EMNLP 2024 (Findings) | Paper · Code · arXiv |
| 2024 | PingPong: A Benchmark for Role-Playing Language Models with User Emulation and Multi-Model Evaluation | arXiv | Paper |
| 2024 | Role-playing Prompt Framework: Generation and Evaluation | arXiv | Paper |
| 2024 | RoleAgent: Building, Interacting, and Benchmarking High-quality Role-Playing Agents from Scripts | NeurIPS 2024 | Paper |
| 2024 | RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models | ACL 2024 (Findings) | Paper · arXiv |
| 2024 | SocialBench: Sociality Evaluation of Role-Playing Conversational Agents | ACL 2024 (Findings) | Paper · Code · arXiv |
| 2024 | Thinking Before Speaking: A Role-playing Model with Mindset | arXiv | Paper |
| 2024 | TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models | ACL 2024 (Findings) | Paper · arXiv |
| 2023 | ChatHaruhi: Reviving Anime Character in Reality via Large Language Model | arXiv | Paper · Code |
| 2023 | RoleEval: A Bilingual Role Evaluation Benchmark for Large Language Models | arXiv | Paper |
Scoring Protocols
Rule-based and learned scores
Survey §V.C · Edit this category · Detailed list · BibTeX
5 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2026 | BOOKMARKS: Efficient Active Storyline Memory for Role-playing | arXiv | Paper |
| 2026 | From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents | arXiv | Paper · Code |
| 2025 | CharacterBench: Benchmarking Character Customization of Large Language Models | AAAI 2025 | Paper |
| 2024 | CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation | ACL 2024 | Paper · Code · arXiv |
| 2023 | RoleEval: A Bilingual Role Evaluation Benchmark for Large Language Models | arXiv | Paper |
LLM judges
Survey §V.C · Edit this category · Detailed list · BibTeX
4 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2025 | FURINA: A Fully Customizable Role-Playing Benchmark via Scalable Multi-Agent Collaboration Pipeline | arXiv | Paper |
| 2025 | Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents | EMNLP 2025 | Paper · arXiv |
| 2023 | G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment | EMNLP 2023 | Paper · Code · arXiv |
| 2023 | Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena | NeurIPS 2023 | Paper · Code |
Human and outcome-based evaluation
Survey §V.C · Edit this category · Detailed list · BibTeX
4 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2025 | CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds | NAACL 2025 | Paper · arXiv |
| 2025 | DEBATE: A Large-Scale Benchmark for Evaluating Opinion Dynamics in Role-Playing LLM Agents | arXiv | Paper |
| 2025 | RolePlot: A Systematic Framework for Evaluating and Enhancing the Plot-Progression Capabilities of Role-Playing Agents | ACL 2025 | Paper |
| 2024 | InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews | ACL 2024 | Paper · arXiv |
Reliability and Limits of Evaluation
Survey §V.D · Edit this category · Detailed list · BibTeX
6 references · newest first
| Year | Paper | Venue | Links |
|---|---|---|---|
| 2026 | Rethinking Role-Playing Evaluation: Anonymous Benchmarking and a Systematic Study of Personality Effects | arXiv | Paper |
| 2025 | FURINA: A Fully Customizable Role-Playing Benchmark via Scalable Multi-Agent Collaboration Pipeline | arXiv | Paper |
| 2025 | Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents | EMNLP 2025 | Paper · arXiv |
| 1997 | PARADISE: A Framework for Evaluating Spoken Dialogue Agents | ACL/EACL 1997 | Paper |
| 1995 | Validity of Psychological Assessment | Am. Psychol. | Paper |
| 1955 | Construct Validity in Psychological Tests | Psychol. Bull. | Paper |
Contribute
Know a relevant paper? Suggest it here with its title, link, and relevant category. You can also submit additions or corrections through a pull request. All submissions are reviewed before inclusion.
See How to contribute for step-by-step instructions.
License
Repository tooling and original documentation are available under the MIT License. Bibliographic facts identify the cited works; rights in the papers and linked resources remain with their respective owners.