NATHANIEL BLACKWOOD. Advancing Strategic Decision Excellence through Self Play Reinforcement Learning Frameworks Leveraging Large Language Models for Recursive Policy Improvement. Computational Intelligence Systems, [S. l.], v. 4, n. 1, 2026. DOI: 10.66280/cis.v1i1.147. Disponível em: https://scivexus.org/index.php/CIS/article/view/147. Acesso em: 27 may. 2026.