Yan Y, Jiang J, Liu Y, Cao Y, Xu X, Zhang M, et al. S^3cMath: Spontaneous Step-Level Self-Correction Makes Large Language Models Better Mathematical Reasoners. AAAI [Internet]. 2025 Apr. 11 [cited 2026 May 20];39(24):25588-96. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/34749