一个被忽视的简单方法，碾压了花哨的AI训练新招
想让AI学会推理，最近流行一种新训练法：不给它标准答案步骤，只让它自己生成思考过程，然后靠预测下一段文字来奖励。听起来很聪明，但一篇对照实验发现，一个老掉牙的简单做法反而完胜：把两种数据——有详细步骤的和没有步骤的——混在一起，直接做一次常规微调。就这么简单，最终效果更好，而且训练成本低了60多倍。研究者还发现一个反直觉的事：训练前准确率高的模型，训练后不一定更强，所以别只看中间指标。这不是你明天能拿来用的技巧，但它提醒我们：AI领域的新方法，未必比朴素方案强。
📄 原文摘要(英文)
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. The method trains a model to generate implicit reasoning traces and rewards them by their ability to predict the next chunk of text. While promising, existing evaluations primarily compare against conventional SFT baselines, leaving open whether the gains come from the RL formulation itself or from more effectively exposing the model to no-CoT data. We address this question with a controlled study of next-chunk reasoning RL and a simple but previously overlooked alternative: Mixed SFT, a single supervised fine-tuning stage that jointly trains on no-CoT and long-CoT data. Despite its simplicity, Mixed SFT achieves a clearly higher post-RLVR performance ceiling than next-chunk reasoning RL while requiring over 60 times less training compute. The advantage is consistent across in-domain mathematical reasoning and out-of-domain reasoning tasks. Moreover, we show that higher pre-RLVR accuracy does not necessarily translate into higher post-RLVR accuracy, highlighting the need to evaluate no-CoT training strategies in the context of the full post-training pipeline.