Yue C, Dong C, Gao Y, He H, Chai J, Lin W, et al. Promoting Efficient Reasoning with Verifiable Stepwise Reward. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 14];40(41):34530-8. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/40752