Comparative Empirical Evaluation of Prompting Strategies for Large-Language-Model Web-Navigation Agents on the WebArena Benchmark. Journal of Science, Innovation & Social Impact, [S. l.], v. 2, n. 4, p. 25–36, 2026. DOI: 10.71222/jbq63281. Disponível em: https://pinnaclepubs.com/index.php/JSISI/article/view/844. Acesso em: 26 jul. 2026.