Hu H. Right Answers, Wrong Reasons: Perception Errors in Multimodal Chain-of-Thought and the Blind Spot of Outcome-Based Rewards. IJAAA [Internet]. 2026 Oct. 10 [cited 2026 Oct. 13];2(10):77-101. Available from: https://www.dawnclarity.press/index.php/ijaaa/article/view/193