AI 自己教自己，参考答案没那么重要
让 AI 自己教自己，很多人以为关键是给老师一份「标准答案」。这篇把 5,319 道数学题配上六种不同详略的参考答案，逐一对比后发现：去掉参考答案、只靠老师直接给答案，学生照样学到大部分能力；完整解题过程带来的额外提升只有两个百分点，而且只在某个模型上出现。更反直觉的是，把老师的「短答」换成「长思考」，学生成绩反而变差。也就是说，AI 从自己身上学到的，主要是「怎么调用已有的推理能力」，而不是答案里写了什么。它不是你明天能用上的东西，但它在提醒：我们可能高估了「给 AI 看更多解题过程」这件事的价值。
📄 原文摘要(英文)
On-policy self-distillation (OPSD) lets a language model learn from a frozen copy of itself that sees an answer or a worked solution. Giving the teacher this extra information seems to offer the student more to learn, but how much does it add beyond distillation itself? To isolate that contribution, we construct AMPLE-Math, a reusable suite of 5,319 mathematical problems with six reasoning views that share the same answer, and compare each view with matched reference-free distillation. With a thinking-enabled teacher supervising direct-response rollouts, reference-free distillation accounts for much of Qwen3-1.7B's improvement under thinking-enabled evaluation, both in domain and on external benchmarks. Evidence for an additional reference benefit is modest in Qwen, strongest for a polished solution, whereas complete traces add two percentage points in SmolLM3-3B at step 50. These benefits depend on the student being trained. At the same checkpoint, replacing short direct-response rollouts with long thinking-enabled rollouts turns gains into losses in both families while the problems, references, and evaluation stay fixed. Teacher profiles and matched loss interventions in Qwen further show that changing token-level supervision can leave student behavior largely unchanged. Together, these findings suggest that OPSD can improve access to existing reasoning capabilities through parameters shared by direct-response and thinking-enabled inference. The value of a privileged reference is what it adds to this cross-mode transfer, not how much of the solution it reveals.