Xin, Q. (2026). LLM-Agent-Style Automated Usability Testing on MiniWoB++: A Reproducible Chunked Full-Run with ReAct, Plan-Execute, and Self-Reflect Policies. Blockchain, Artificial Intelligence, and Future Research, 2(1), 56–82. https://doi.org/10.70211/bafr.v2i1.384