Create and explore imaginative 3D worlds with our new product Dreamfield (opens in a new tab)
Papers
Topics
Authors
Recent
Search
2000 character limit reached

DTDD: Divergence-Triggered Dynamic Distillation for Reliable On-Policy Supervision

Published 13 Oct 2026 in cs.LG and cs.AI | (2610.19302v1)

Abstract: On-policy distillation (OPD) provides dense token-level supervision on student rollouts, but this supervision can become unreliable when the student and teacher diverge, either because of a large initial policy gap or compounding errors in long-horizon reasoning and tool use. We introduce Divergence-Triggered Dynamic Distillation (DTDD), an adaptive OPD framework that uses segment-level student-teacher divergence to trigger teacher takeover during training. When divergence triggers an intervention during reasoning, the student prefix continues to receive standard OPD supervision. The teacher then generates a recovery suffix, which the student learns through behavior cloning, using cross-entropy on the teacher-generated tokens. We evaluate DTDD in three regimes: long-horizon reasoning, distillation from a base initialization without offline supervised fine-tuning (SFT), and multi-turn agents. We also compare alternative trigger designs and teacher-intervention rates. DTDD reduces the post-warmup peak gradient norm by 8.6×8.6\times and, from a base initialization, reaches 21.3%21.3\% held-out math accuracy in 2.6×2.6\times fewer optimizer updates than OPD; both methods finish near 22%22\%. It improves best-observed performance by $4.8$ and $4.1$ percentage points on ALFWorld with LoRA and agentic code, respectively. Ablations show that segment-averaged triggers outperform token-spike triggers. Behavior cloning is also more effective than the tested OPD surrogate for training teacher-generated recoveries. Across 23 experimental arms, takeover tends to help when the teacher substantially outperforms the OPD-trained student, provided that the teacher can recover from student-visited states, the student can learn those recoveries, and teacher intervention is neither excessive nor insufficient.

Summary

No one has generated a summary of this paper yet.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.