Metraipolis › archive › dc_bf6d40e5cbdc
DuoOPD: Learning from Joint Teacher-Student Outcomes for Multi-Task On-Policy Distillation — arXiv:2609.33711
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.33711
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T22:37:43.113Z
- SHA-256 of the archived text
6bd056dd4e36926495ab9f12e5d974805a16883c68b6ae847fc091fb25ee8be8- Stable URL of this page
https://metraipolis.com/documento/dc_bf6d40e5cbdc
How to cite
DuoOPD: Learning from Joint Teacher-Student Outcomes for Multi-Task On-Policy Distillation — arXiv:2609.33711 — arXiv (en), https://arxiv.org/abs/2609.33711 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf6d40e5cbdc (Metraipolis archive dc_bf6d40e5cbdc, sha256 6bd056dd4e36926495ab9f12e5d974805a16883c68b6ae847fc091fb25ee8be8)
BibTeX
@misc{dcbf6d40e5cbdc,
title = {DuoOPD: Learning from Joint Teacher-Student Outcomes for Multi-Task On-Policy Distillation — arXiv:2609.33711},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.33711},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf6d40e5cbdc; sha256 6bd056dd4e36926495ab9f12e5d974805a16883c68b6ae847fc091fb25ee8be8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33711. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
On-policy distillation (OPD) trains a student on its own responses with token-level feedback from a stronger teacher, yet the teacher can fail on questions the student already answers correctly, and how often each model succeeds varies across tasks. OPD ignores these outcomes and, on average, pushes down even the student's correct responses; gating feedback by student correctness fixes the direction but uses the teacher in the same way whether or not it succeeded. We introduce DuoOPD, in which the student's outcome sets the direction of feedback and the joint teacher-student outcome decides how the teacher supports it: when only the teacher succeeds, its verified answer becomes context for scoring the student's failed response, and when only the student succeeds, a weight shared within the task reinforces the whole response. A single rule covers all four outcome combinations without task-specific settings. Across Qwen3 and Llama, DuoOPD outperforms all five baselines in mean macro accuracy, improving over OPD by 2.58 and 5.98 percentage points, and it also leads on two further task mixtures spanning scientific calculation, instruction following, and code generation. Ablations show that outcome-based direction alone stays near the gated baseline, while the joint-outcome designs supply most of the gain. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.33711 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T22:14:28.024Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).