3 papers
cs.HC2026
XAgen: An Explainability Tool for Identifying and Correcting Failures in Multi-Agent Workflows
Xinru Wang, Ming Yin, Eunyee Koh +1
As multi-agent systems powered by Large Language Models (LLMs) are increasingly adopted in real-world workflows, users with diverse technical backgrounds are now building and refin…
cs.HC2026
SimAB: Simulating A/B Tests with Persona-Conditioned AI Agents for Rapid Design Evaluation
Tim Rieder, Marian Schneider, Mario Truss +6
A/B testing is a standard method for validating design decisions, yet its reliance on real user traffic limits iteration speed and makes certain experiments impractical. We present…
cs.HC2026
UXCascade: Scalable Usability Testing with Simulated User Agents
Steffen Holter, Eunyee Koh, Mustafa Doga Dogan +1
Simulated user agents are increasingly deployed in usability testing to support fast, iterative UX workflows, as they generate rich data such as action logs and think-aloud reasoni…