A Survey on LLM-based Conversational User Simulation
Abstract
User simulation has long played a vital role in computer science due to its potential to support a wide range of applications. Language, as the primary medium of human communication, forms the foundation of social interaction and behavior. Consequently, simulating conversational behavior has become a key area of study. Recent advancements in large language models (LLMs) have significantly catalyzed progress in this domain by enabling high-fidelity generation of synthetic user conversation. In this paper, we survey recent advancements in LLM-based conversational user simulation. We introduce a novel taxonomy covering user granularity and simulation objectives. Additionally, we systematically analyze core techniques and evaluation methodologies. We aim to keep the research community informed of the latest advancements in conversational user simulation and to further facilitate future research by identifying open challenges and organizing existing work under a unified framework.
Cite
@article{arxiv.2604.24977,
title = {A Survey on LLM-based Conversational User Simulation},
author = {Bo Ni and Leyao Wang and Yu Wang and Branislav Kveton and Franck Dernoncourt and Yu Xia and Hongjie Chen and Reuben Leura and Samyadeep Basu and Subhojyoti Mukherjee and Puneet Mathur and Nesreen Ahmed and Junda Wu and Li Li and Huixin Zhang and Ruiyi Zhang and Tong Yu and Sungchul Kim and Jiuxiang Gu and Zhengzhong Tu and Alexa Siu and Zichao Wang and David Seunghyun Yoon and Nedim Lipka and Namyong Park and Zihao Lin and Trung Bui and Yue Zhao and Tyler Derr and Ryan A. Rossi},
journal= {arXiv preprint arXiv:2604.24977},
year = {2026}
}
Comments
Submitted in August 2025. MOD-81000 approved survey