Hu, Haosong. “Right Answers, Wrong Reasons: Perception Errors in Multimodal Chain-of-Thought and the Blind Spot of Outcome-Based Rewards”. International Journal of Advanced AI Applications 2, no. 10 (October 10, 2026): 77–101. Accessed October 13, 2026. https://www.dawnclarity.press/index.php/ijaaa/article/view/193.