PAST adapts a self-distillation teacher using complete correct and failed student trajectories, then distills the adapted teacher back to the prefix-only student, gaining 5.6pp Avg@12 over Vanilla OPSD.
Is More Privileged Information Better? From Solution Traces to Problem-Solving Structure in Self-Distilled Reasoning
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
On-policy self-distillation (OPSD) improves reasoning by using a privileged view of a model conditioned on reference solutions to supervise a student view that observes only the question. However, the teacher-provided token-level targets may depend on reference-specific information unavailable at inference time. We propose Problem-Space-Guided OPSD (PS-OPSD), which replaces the complete solution with trajectory-grounded guidance describing the initial state, goal conditions, constraints, and a selected state-transition path. The student rollout and OPSD objective remain unchanged. Across three mathematical reasoning benchmarks and model scales ranging from 1.7B to 8B, PS-OPSD achieves the highest aggregate question-only accuracy among the compared methods. Controlled experiments further indicate that guidance relevance and path coherence contribute to these gains, highlighting the representation of privileged information as an important design choice in OPSD.
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PAST: Privileged Adaptation from Complete Student Trajectories for On-Policy Self-Distillation
PAST adapts a self-distillation teacher using complete correct and failed student trajectories, then distills the adapted teacher back to the prefix-only student, gaining 5.6pp Avg@12 over Vanilla OPSD.