论文用实验数据揭示了一个反直觉现象：学生在模仿老师时，67%的token在“同意但失败”，说明局部蒸馏有盲区。做模型蒸馏的朋友可以看看这个诊断方法。
在线策略蒸馏（OPD）中教师提供的token级似然度常被局部解读，但本研究发现这种解读受到最终回答正确性的混淆。论文引入一种结果解析诊断方法，交叉评估点状师生分歧与最终答案正确性。在Qwen3-8B学生与Qwen3-32B教师的数学推理实验中，67.84%的响应token属于“同意但失败”（agreement-on-failure）；Qwen2.5-7B/32B组合为67.68%。即使教师四轮均正确回答的提示，学生准确率达86.91%，但仍有14.76%的token存在同意但失败。三种训练策略（模仿、遮蔽、对比）均未能显著改善该现象，表明需要过程标签或教师延续等额外位置信息来解决定位局限。
Outcome-Confounded Local Supervision in On-Policy Distillation
On-policy distillation (OPD) trains a student on its own trajectories while a teacher supplies dense token-level likelihoods at student-visited prefixes. These likelihoods are often read locally: agreement appears safe to imitate, whereas disagreement appears to identify an error. We show that both readings are confounded by the outcome of the completed trajectory. We introduce an outcome-resolved diagnostic that crosses pointwise teacher-student divergence with final-answer correctness, separating safe imitation, productive divergence, harmful divergence, and agreement-on-failure. In an eight-seed mathematical-reasoning study with a Qwen3-8B student and Qwen3-32B teacher, agreement-on-failure constitutes 67.84% of pooled response-token mass; with a Qwen2.5-7B/32B pair it remains 67.68%. The result persists across threshold, sequence-level, format, and truncation audits. Even on prompts that the Qwen3 teacher solves in all four independent attempts, student accuracy rises to 86.91% but agreement-on-failure remains 14.76%. We then run three matched training probes that use the available signals to imitate, mask, or contrast whole trajectories; none consistently reduces agreement-on-failure. The result points to a localization limitation: local divergence paired with a trajectory-level outcome does not identify where a failed trajectory became unrecoverable. Addressing this limitation requires additional positional information, such as process labels, teacher continuations from student prefixes, or token-level alignment across rollouts. Our contribution is therefore diagnostic rather than a new training method.