A Survey on LLM-based Conversational User Simulation
A Survey on LLM-based Conversational User Simulation
基于大语言模型的对话用户模拟综述
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.
摘要： 用户模拟因其支持广泛应用场景的潜力，长期以来在计算机科学领域发挥着至关重要的作用。语言作为人类交流的主要媒介，构成了社会互动与行为的基础。因此，模拟对话行为已成为一个关键的研究领域。
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.
大语言模型（LLMs）的最新进展通过实现高保真的合成用户对话生成，极大地推动了该领域的发展。在本文中，我们综述了基于大语言模型的对话用户模拟的最新进展。
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.
我们引入了一种涵盖用户粒度和模拟目标的新型分类法。此外，我们系统地分析了核心技术和评估方法。我们旨在让研究界了解对话用户模拟的最新进展，并通过识别开放性挑战以及在统一框架下整理现有工作，进一步促进未来的研究。
Paper Details:
- Authors: Bo Ni, Leyao Wang, Yu Wang, et al.
- Submission Date: 27 Apr 2026
- Subjects: Computation and Language (cs.CL); Human-Computer Interaction (cs.HC)
- DOI: 10.48550/arXiv.2604.24977
论文详情：
- 作者： Bo Ni, Leyao Wang, Yu Wang 等人
- 提交日期： 2026年4月27日
- 学科分类： 计算与语言 (cs.CL)；人机交互 (cs.HC)
- DOI： 10.48550/arXiv.2604.24977