mlsanityData to 7 Oct 2026

A Survey on LLM-based Conversational User Simulation

arXiv 2604.24977 ↗First posted 27 Apr 2026cs.CL cs.HCcited by 14

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 126 of its 200 references that are in the map. First posted on arXiv 27 Apr 2026.

Builds on

126 of 200 references.

References · 126

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  5. 2017Deep reinforcement learning from human preferencescited by 3,846
  6. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  7. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  8. 2024A Survey on LLM-as-a-Judgecited by 1,384
  9. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  10. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
  11. 2023Enhancing Chat Language Models by Scaling High-quality Instructional Conversationscited by 825
  12. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
38 more
  1. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  2. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  3. 2023LaMP: When Large Language Models Meet Personalizationcited by 425
  4. 2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 356
  5. 2023Character-LLM: A Trainable Agent for Role-Playingcited by 335
  6. 2021Beyond Goldfish Memory: Long-Term Open-Domain Conversationcited by 266
  7. 2023ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systemscited by 259
  8. 2024RAFT: Adapting Language Model to Domain Specific RAGcited by 258
  9. 2023PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traitscited by 229
  10. 2016A Persona-Based Neural Conversation Modelcited by 221
  11. 2024ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RLcited by 212
  12. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 206
  13. 2017Deal or No Deal? End-to-End Learning for Negotiation Dialoguescited by 202
  14. 2024Agent Q: Advanced Reasoning and Learning for Autonomous AI Agentscited by 201
  15. 2015A Neural Conversational Modelcited by 195
  16. 2019BERT for Joint Intent Classification and Slot Fillingcited by 195
  17. 2024Trial and Error: Exploration-Based Trajectory Optimization for LLM Agentscited by 194
  18. 2024Large Language Models for Education: A Survey and Outlookcited by 185
  19. 2025AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Societycited by 180
  20. 2024Quantifying the Persona Effect in LLM Simulationscited by 164
  21. 2015Doubly Robust Policy Evaluation and Optimizationcited by 158
  22. 2018Decoupling Strategy and Generation in Negotiation Dialoguescited by 156
  23. 2016Unbiased Learning-to-Rank with Biased Feedbackcited by 155
  24. 2019Taskmaster-1: Toward a Realistic and Diverse Dialog Datasetcited by 139
  25. 2024CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluationcited by 139
  26. 2023User Behavior Simulation with Large Language Model based Agentscited by 136
  27. 2024Simulating Classroom Education with LLM-Empowered Agentscited by 125
  28. 2024Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimizationcited by 112
  29. 2023SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversationscited by 109
  30. 2024Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignmentcited by 104
  31. 2025Reinforcement Learning for Long-Horizon Interactive LLM Agentscited by 103
  32. 2024Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Modelscited by 99
  33. 2025AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectoriescited by 99
  34. 2019RecSim: A Configurable Simulation Platform for Recommender Systemscited by 91
  35. 2021MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluationcited by 86
  36. 2025LLM Generated Persona is a Promise with a Catchcited by 77
  37. 2015Cascading Bandits: Learning to Rank in the Cascade Modelcited by 75
  38. 2019Personalized Dialogue Generation with Diversified Traitscited by 73

50 most cited of 126 All 126 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 14.

14 papers.

Sort:

By area:

  1. 2026FORTIS: Benchmarking Over-Privilege in Agent Skillscited by 11
  2. 2026Quantifying the Utility of User Simulators for Building Collaborative LLM Assistantscited by 6
  3. 2026Learning User Simulators with Turing Rewardscited by 3
  4. 2026HomeFlow: A Data Flywheel for Smart Home Agent Training with Verifiable Simulationcited by 2
  5. 2026Skill-CMIB: Multimodal Agent Skill for Consistent Action via Conditional Multimodal Information Bottleneckcited by 1
  6. 2026MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimizationcited by 1
  7. 2026Don't Guess, Just Ask: Resolving Ambiguity in Referring Segmentation via Multi-turn Clarificationcited by 1
  8. 2026SCICONVBENCH: Benchmarking LLMs on Multi-Turn Clarification for Task Formulation in Computational Sciencecited by 1
  9. 2026Large Behavior Model: A Promptable Digital Twin of the Retail Customercited by 1
  10. 2026Studying People to Study AI: Expert Perspectives on the Epistemic Fit and Barriers of Human Research in AI Safety & Ethicscited by 0
  11. 2026KnowSim: Evaluating Information Calibration in LLM Assistants with User Simulators that Learncited by 0
  12. 2026Investigating Assistant Bias in LLM User Simulators Using a Role Vectorcited by 0
2 more
  1. 2026When Does Defendant Statement Matter? A Study of Bias and Persuasion in LLM-Simulated Jurorscited by 0
  2. 2026Pretrained Persona Mixture Models and Tandem Models for Human Simulationcited by 0