QUENTIN LARSEN; TAOLI TIAN. Risk-Aware Reinforcement Learning for Safe Strategic Reasoning in Large Language Model Agents. Artificial Intelligence and Machine Learning Systems, [S. l.], v. 1, n. 1, 2026. Disponível em: https://aimls.org/index.php/home/article/view/119. Acesso em: 3 jun. 2026.