PROF. TAREQ N. HASHEM. Reasoning capabilities of large language models: a systematic review and meta-analysis of benchmarks, methods, and emergent behaviours (2018–2025). Journal of Artificial Intelligence,Machine Learning and Neural Network , [S. l.], v. 5, n. 1, p. 63–75, 2025. Disponível em: https://hmjournals.com/journal/index.php/JAIMLNN/article/view/6320. Acesso em: 20 may. 2026.