AI RESEARCH
SimGym: A Framework for A/B Test Simulation in E-Commerce with Traffic-Grounded VLM Agents
arXiv CS.AI
•
ArXi:2605.19219v1 Announce Type: new A/B testing remains the gold standard for evaluating modifications to e-commerce fronts, yet it diverts traffic, requires weeks to reach statistical significance, and risks degrading user experience. We present SimGym, a framework for simulating A/B tests on e-commerce fronts using vision-language model (VLM) agents operating in a live browser.