PerceptUI: LLM Agents as Human-Aligned Synthetic Users for UI/UX Evaluation
For UI/UX designers and product developers, PerceptUI provides a scalable, cost-effective alternative to human evaluation that produces realistic, persona-specific feedback.
PerceptUI introduces a framework for persona-conditioned UI/UX evaluation that predicts how specific users would answer interface-related questions, achieving human-level realism and generalizing to unseen questions and personas.
User interface (UI) and user experience (UX) evaluation is central to product development, yet reliable feedback still relies on recruiting human participants or running online A/B tests, making early-stage iteration slow and costly. In light of this, recent work has explored Multimodal Large Language Models as proxy evaluators. However, existing approaches either produce surface-level critiques or a judgment that reflects the model's own biases rather than the genuine response of a particular user. We introduce PerceptUI, a framework for persona-conditioned UI/UX evaluation that predicts how a specific user would answer interface-related questions and produces natural-language rationales. PerceptUI is trained in two stages: (i) contrastive reflection fine-tuning distills teacher-generated rationales by extracting lessons from human decisions, and (ii) a reflective prompt-evolution step from the model's own failure traces. Across multiple domains and datasets, PerceptUI achieves human-level realism, generalizes to unseen questions and personas, and yields population-level response distributions.