When Top-K Misses the Decision: Tool-Call Drift in Multi-Teacher On-Policy Distillation

תקציר מקורי באנגליתarXiv:2607.07050v3 Announce Type: replace Abstract: Top-K teacher logits make on-policy distillation tractable, but probability mass is not the same as decision support. In a two-teacher tool-use setting, vanilla generalized knowledge distillation raises tool-call recall while also calling on examples that require direct answers. The response teacher's top-32 retains 99.99% of its probability mass yet contains the tool-call behavior-switch token on only 0.4% of 1,500 audited prompts; even top-256 covers only 52.2%. Because omitted logits receive zero direct gradient under the truncated objective, the tool teacher reinforces entry while the response teacher usually cannot oppose it. Frozen replay shows that a wrong entry then amplifies divergence along the generated trajectory. Restoring th