PHILIP KENSINGTON; SCOTT WHITFIELD. Enhancing Logical Reasoning Depth via Monte Carlo Tree Search Integrated Reinforcement Learning for Advanced Large Language Model Thinking Processes. International Journal of Artificial Intelligence Research, [S. l.], v. 1, n. 2, 2026. DOI: 10.66280/ijair.v1i2.153. Disponível em: https://www.isipress.org/index.php/IJAIR/article/view/153. Acesso em: 17 may. 2026.