Large Language Model-Based Role-Play Simulation

Follow this topic Ask about this topic

This field studies how language models can simulate people and characters in interactive settings, from fictional worlds and customer conversations to clinical, educational, and social scenarios. Common approaches combine persona prompts with dialogue memory, psychological or knowledge-state models, multi-agent designs, and fine-tuning or reinforcement learning to shape behavior over multiple turns. Researchers evaluate realism, persona consistency, task outcomes, and safety using human judgments, dialogue benchmarks, and comparisons with real-world behavior. A central challenge is that fluent role-play can still fail to reflect a person's knowledge, motivations, or boundaries, while longer interactions can expose drift, bias, and unsafe responses.

Latest papers

111 papers21 papers in the last four weeks, up 62% on the four weeks before. 0.1% of all new papers.

Interplay: Training Independent Simulators for Reference-Free Conversational Recommendation
Mar 19, 2026Jerome Ramos, Feng Xia, Xi Wang +4Recommender Systems User Simulation
University College London, London, UK · University of Sheffield, Sheffield, UK · Missouri University of Science and Technology, Rolla, USA
Elder-Sim: A Psychometrically Validated Platform for Personality-Stable Elderly Digital Twins
Mar 16, 2026Jiaqing Wang, Zhongfang Yang, Xingyuan Zhu +8Digital Twins LLM Agent Reliability
Yulin AI-Enhanced HealthCare Lab, Shanghai, China · School of Nursing, Fudan University, Shanghai, China · School of Nursing, Medical College of Soochow University, Suzhou, Jiangsu Province, China +7
Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLMs
Mar 14, 2026Kai Wang, Haoyang You, Yang Zhang +1Large Language Model-Based Role-Play Simulation LLM Prompting
Harbin Institute of Technology, China · Macquarie University, Australia
EducaSim: Interactive Simulacra for CS1 Instructional Practice
Mar 12, 2026Cameron Mohne, Nicholas Vo, Dora Demszky +1AI in Education Computer Science Education
Stanford University, California, USA
Enhancing Consistency of Werewolf AI through Dialogue Summarization and Persona Information
Mar 7, 2026Yoshiki Tanaka, Takumasa Kaneko, Hiroki Onozeki +6Game-Playing Agents Large Language Model-Based Role-Play Simulation
The University of Electro-Communications
Moral Mazes in the Era of LLMs
Mar 6, 2026Dang Nguyen, Harvey Yiyun Fu, Peter West +2Pragmatic Reasoning in Language Models Language Model Generation Evaluation
University of Chicago · University of British Columbia
An Interactive LLM-Based Simulator for Dementia-Related Activities of Daily Living
Mar 6, 2026Kruthika Gangaraju, Shu-Fen Wung, Kevin Berner +2Dementia Care Large Language Model-Based Role-Play Simulation
Worcester Polytechnic Institute Worcester, Massachusetts, USA · University of California Davis Sacramento, CA, USA · MGH Institute of Health Professionals Boston, MA, USA +1
AI-Assisted Moot Courts: Simulating Justice-Specific Questioning in Oral Arguments
Mar 5, 2026Kylie Zhang, Nimra Nadeem, Lucia Zheng +2Large Language Model-Based Role-Play Simulation Language Model Generation Evaluation
Princeton University, Princeton, NJ, USA · Stanford University, Stanford, USA
Assessing the Effectiveness of LLMs in Delivering Cognitive Behavioral Therapy
Mar 4, 2026Navdeep Singh Bedi, Ana-Maria Bucur, Noriko Kando +1Clinical Language Model Evaluation Medical LLMs
Università della Svizzera italiana, Switzerland · National Institute of Informatics, Japan
Eval4Sim: An Evaluation Framework for Persona Simulation
Mar 3, 2026Eliseo Bao, Anxo Perez, Javier Parapar +1Large Language Model-Based Role-Play Simulation Large Language Model-Based Social Simulation
IRLab, CITIC, Universidade da Coruña A Coruña, Spain · University of Sheffield Sheffield, United Kingdom
Enhancing Persona Following at Decoding Time via Dynamic Importance Estimation for Role-Playing Agents
Mar 2, 2026Yuxin Liu, Mingye Zhu, Siyuan Liu +2Large Language Model-Based Role-Play Simulation Persona-Conditioned Generation
University of Science and Technology of China
TriageSim: A Conversational Emergency Triage Simulation Framework from Structured Electronic Health Records
Mar 2, 2026Dipankar Srirag, Quoc Dung Nguyen, Aditya Joshi +2Clinical Triage User Simulation
University of New South Wales, Sydney, Australia
Individual Turing Test: A Case Study of LLM-based Simulation Using Longitudinal Personal Data
Mar 1, 2026Minghao Guo, Ziyi Ye, Wujiang Xu +3Large Language Model-Based Role-Play Simulation Personalized Language Models
Rutgers University, New Brunswick, NJ, USA · Fudan University, Shanghai, China · Microsoft, New York, NY, USA
Sydney Telling Fables on AI and Humans: A Corpus Tracing Memetic Transfer of Persona between LLMs
Feb 25, 2026Jiří Milička, Hana BednářováPersonality Modeling in Language Models Persona-Conditioned Generation
Charles University, Prague
Dynamic Personality Adaptation in Large Language Models via State Machines
Feb 25, 2026Leon Pielage, Ole Hätscher, Mitja Back +2Medical Education Personality Modeling in Language Models
Institute for Geoinformatics, University of Münster, 48149 Münster, Germany · Faculty of Mathematics and Computer Science, University of Münster, 48149 Münster, Germany · Department of Psychology, University of Münster, 48149 Münster, Germany +1
Assessing Risks of Large Language Models in Mental Health Support: A Framework for Automated Clinical AI Red Teaming
Feb 23, 2026Ian Steenstra, Paola Pedrelli, Weiyan Shi +2LLM Safety Evaluation Clinical Language Model Evaluation
Northeastern University Boston, MA, USA · Harvard Medical School Boston, MA, USA
Facet-Level Persona Control by Trait-Activated Routing with Contrastive SAE for Role-Playing LLMs
Feb 22, 2026Wenqiu Tang, Zhen Wan, Takahiro Komamizu +1Persona-Conditioned Generation Large Language Model-Based Role-Play Simulation
Nagoya University, Nagoya, Aichi, Japan · Kyoto University, Kyoto, Japan
CALM-IT: Enhancing Synthetic Motivational Interviewing Dialogue Quality with Conversational Dynamics
Jan 15, 2026Viet Cuong Nguyen, Nhi Yen Nguyen, Kristin A. Candan +5Large Language Model-Based Role-Play Simulation Synthetic Data Generation for Language Models
Georgia Institute of Technology · Northwell Health · Columbia University
PsyCLIENT: Client Simulation via Conversational Trajectory Modeling for Trainee Practice and Model Evaluation in Mental Health Counseling
Jan 12, 2026Huachuan Qiu, Zhaoming Chen, Yuqian Chen +3Large Language Model-Based Role-Play Simulation User Simulation
Westlake University · The University of Utah
"Is This Really a Human Peer Supporter?": Misalignments Between Peer Supporters and Experts in LLM-Supported Interactions
Jun 11, 2025Kellie Yu Hui Sim, Roy Ka-Wei Lee, Kenny Tsu Wei ChooLarge Language Model-Based Role-Play Simulation Emotional Support Conversation
Singapore University of Technology and Design, Singapore
Simulating Student-Tutor Interactions with LLMs for Multilingual Math Feedback
Jun 5, 2025Junior Cedric Tonga, KV Aditya Srivatsa, Kaushal Kumar Maurya +2Educational Feedback Generation Generative AI in Education
Mohamed bin Zayed University of Artificial Intelligence

Mar 19, 2026J/K move · Enter open · S save

Interplay: Training Independent Simulators for Reference-Free Conversational Recommendation

Jerome Ramos, Feng Xia, Xi Wang, Shubham Chatterjee+3

University College London, London, UK · University of Sheffield, Sheffield, UK · Missouri University of Science and Technology, Rolla, USA

Recommender Systems User Simulation Synthetic Data Generation for Language Models Large Language Model-Based Role-Play Simulation Multi-Agent LLM Systems

Open paper AskPDF arXiv

Training conversational recommender systems (CRS) requires extensive dialogue data, which is challenging to collect at scale. To address this, researchers have used simulated user-recommender conversations. Traditional simulation approaches often utilize a single large language model (LLM) that generates entire conversations with prior knowledge of the target items, leading to scripted and artificial dialogues. We propose a reference-free simulation framework that trains two independent LLMs, one as the user and one as the conversational recommender. These models interact in real-time without access to predetermined target items, but preference summaries and target attributes, enabling the recommender to genuinely infer user preferences through dialogue. This approach produces more realistic and diverse conversations that closely mirror authentic human-AI interactions. Our reference-free simulators match or exceed existing methods in quality, while offering a scalable solution for generating high-quality conversational recommendation data without constraining conversations to pre-defined target items. We conduct both quantitative and human evaluations to confirm the effectiveness of our reference-free approach.