From Decomposition to Integration: Stage-Specialized On-Policy Distillation for Video Diagnosis

Fine-grained video diagnosis requires identifying the relevant subject, discovering subtle differences, and deciding which differences constitute a defect. We present a framework that turns these interdependent capabilities into structured supervision and integrates them within one model. A multipass annotation pipeline decomposes reference-conditioned diagnosis into Subject Binding, Multidimensional Comparison, and Issue Filtering, producing compact traces that connect visual evidence to diagnostic decisions. We then introduce Stage-Specialized On-Policy Distillation (Stage OPD): the student generates a complete trajectory, and each specialist provides feedback for its stage under the student's own preceding outputs. Annotated-trace replay supplies complementary supervision for content, stage transitions, and diagnostic decisions. With 2,160 training traces, the resulting 9B student improves both precision and recall on a human-reviewed benchmark, raising issue-detection $F_1$ from 36.68% to 41.88%. The student exceeds a three-call SFT chain in $F_1$ and approaches the 27B reference within 0.31 $F_1$ points while retaining a single 9B model at inference. Overall, Stage OPD organizes specialized supervision through decomposition and integrates the resulting diagnostic capabilities into one model.