Yinhao Tang

Published on Aug 24 · Submitted by Yinhao Tang on Aug 27 Abstract Mixed supervised fine-tuning on combined reasoning corpora outperforms next-chunk reinforcement learning in efficiency and final accuracy across mathematical and out-of-domain tasks. Recent work proposes next-chunk reasoning RL for leveraging no-CoT data---corpora such as worked solutions and textbook derivations that contain reasoning-rich content but lack explicit chain-of-thought annotations.