Zhang, Zijing, and Boning Zhang. “When Instinct Guides and Insight Grounds: Staged RL Training for LLM Agents”. Proceedings of the AAAI Conference on Artificial Intelligence 40, no. 41 (March 14, 2026): 34906–34914. Accessed May 14, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/40794.