A/B testing remains the gold standard for evaluating e-commerce UI changes, yet it diverts traffic, takes weeks to reach significance, and risks harming user experience. We introduce SimGym, a scalable system for rapid offline A/B testing using traffic-grounded synthetic buyers powered by Large Language Model agents operating in a live browser. SimGym extracts per-shop buyer profiles and intents from production interaction data, identifies distinct behavioral archetypes, and simulates cohort-weighted sessions across control and treatment storefronts. We validate SimGym against real human outcomes from real UI changes on a major e-commerce platform under confounder control. Even without alignment post training, SimGym agents achieve state of the art alignment with observed outcome shifts and reduces experiment cycles from weeks to under an hour , enabling rapid experimentation without exposure to real buyers.
@article{arxiv.2602.01443,
title = {SimGym: Traffic-Grounded Browser Agents for Offline A/B Testing in E-Commerce},
author = {Alberto Castelo and Zahra Zanjani Foumani and Ailin Fan and Keat Yang Koay and Vibhor Malik and Yuanzheng Zhu and Han Li and Meysam Feghhi and Ronie Uliana and Shuang Xie and Zhaoyu Zhang and Angelo Ocana Martins and Mingyu Zhao and Francis Pelland and Jonathan Faerman and Nikolas LeBlanc and Aaron Glazer and Andrew McNamara and Lingyun Wang and Zhong Wu},
journal= {arXiv preprint arXiv:2602.01443},
year = {2026}
}