ZHANG, Zijing; ZHANG, Boning. When Instinct Guides and Insight Grounds: Staged RL Training for LLM Agents. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 41, p. 34906–34914, 2026. DOI: 10.1609/aaai.v40i41.40794. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/40794. Acesso em: 14 may. 2026.