PersonaEval: Persona-Based User Simulation for Evaluating Interactive Applications

Real user studies are important for understanding how people interact with systems under test or already deployed. In practice, however, they are often costly, time-consuming, and difficult to scale. To address these challenges, we introduce PersonaEval, a persona-based user simulation framework that approximates real-user behavior across diverse interactive settings. PersonaEval connects simulated users drawn from existing persona datasets to task-specific application interfaces and collects the interaction trajectories and outcomes. PersonaEval provides a plug-and-play evaluation workflow in which the application being evaluated can be easily changed. In this demo, we present PersonaEval on three forms of interactive applications: surveys, chatbots, and web applications. Together, these examples show that PersonaEval can support repeatable, parallelizable, and scalable evaluation across different interaction settings, while producing user-oriented feedback and task-specific behavior.

Introduction. Interactive applications can produce different outcomes across users because they bring different goals and preferences to the same system. Understanding this variation is important during early development. Real user studies remain the most reliable way to measure human experience, but their cost, recruitment burden, and slow iteration cycle make them difficult to use for rapid evaluation (Xuan et al., 2025; Lu et al., 2025). Persona-based simulation offers a practical complement by simulating users with specified profiles and having them interact with a target system. Recent work has developed richer persona representations (Zhang et al., 2018; Ge et al., 2024; NVIDIA, 2025; Wang et al., 2025b), while LLM-based agent frameworks make it easier to deploy these personas as interactive agents (Park et al., 2023; Vezhnevets et al., 2023; Yang et al., 2024; Microsoft, 2025). However, many existing pipelines are designed for a single task format, limiting the reuse of the same persona population across systems and interaction settings.

Discussion / Conclusion. We presented PersonaEval, a plug-and-play system for persona-based user simulation for evaluating interactive applications. Across survey, chatbot, and web settings, PersonaEval shows application-level differences, persona-group variation, and persona alignment patterns. These findings position PersonaEval as a useful tool for simulating real-user studies of interactive systems. Future work should calibrate simulations against human data and expand to broader domain of applications. Limitations and Future Work. Our current demo covers a limited set of survey, chatbot, and web applications. Future work will expand the application coverage and conduct more fine-grained analyses of persona-driven behavior. We also plan to validate simulation quality more rigorously through comparisons with real-user behavior, human evaluation of persona alignment, and deeper analysis of whether users’ goals, interactions, and evaluations are consistently grounded in their assigned personas.