User Simulation in the Era of Generative AI: User Modeling, Synthetic Data Generation, and System Evaluation

TL;DR

This paper reviews the evolving role of user simulation in Generative AI, emphasizing its applications in modeling, synthetic data creation, and system evaluation, while addressing ethical and theoretical aspects.

Contribution

It provides a foundational synthesis of user simulation research, highlighting the shift to generative approaches and proposing an ecosystem for advancing the field.

Findings

Shift from predictive to generative models in user simulation

Controlled simulation enhances fairness and safety in AI systems

Realistic simulators are key to overcoming data and evaluation challenges

Abstract

User simulation is an emerging interdisciplinary topic with multiple critical applications in the era of Generative AI. It involves creating an intelligent agent that mimics the actions of a human user interacting with an AI system, enabling researchers to model and analyze user behaviour, generate synthetic data for training, and evaluate interactive AI systems in a controlled and reproducible manner. Because of its broad scope, research on this topic currently remains scattered across artificial intelligence, human-computer interaction, information science, computational social science, and psychology. To address this fragmented landscape of current research, this article presents a foundational synthesis. We highlight the paradigm shift from traditional predictive models to modern generative approaches, and explicitly frame critical ethical considerations -- demonstrating how controlled simulation serves not merely as a risk vector for bias, but as a powerful, proactive tool to ensure fair representation and system safety. Furthermore, we establish the theoretical connection between user simulation and the pursuit of Artificial General Intelligence, arguing that realistic simulators are indispensable catalysts for overcoming critical data and evaluation bottlenecks and optimizing personalization. Ultimately, we propose a practical, self-sustaining innovation ecosystem bridging academia and industry to advance this increasingly important technology.