The paper introduces Iterative Calibration and Learning (IterCaL), a method for large language model distillation that mitigates teacher bias when target-domain reward feedback is unavailable. IterCaL alternates between calibrating the source-reward teacher via token-level branching and training the student on target prompts, achieving polynomial convergence to an oracle student. The authors prove that regularized direct teacher matching cannot reach the oracle, whereas IterCaL converges to it using only source rewards.
arXiv:2609.17474v1 Announce Type: cross Abstract: Large language model (LLM) distillation aims to transfer the capabilities of a powerful teacher to a smaller student. Direct imitation, however, can...
arXiv:2609.38025v1 Announce Type: cross Abstract: On-policy distillation (OPD) trains a student on its own generated responses using dense, token-level supervision from a stronger teacher. Vanilla OP...
The paper introduces Preference‑Based Self‑Distillation (PBSD), a new on‑policy self‑distillation method that replaces traditional KL matching with a reward‑regularized objective. PBSD derives a reward‑reweighted teacher distribution, optimizing preference gaps between teacher and student samples while keeping on‑policy sampling. Experiments on mathematical reasoning and tool‑use tasks show PBSD achieves stronger average performance, improved training stability, and maintains token efficiency compared to prior self‑distillation baselines.
On-policy distillation (OPD) trains a student on its own generated responses using dense, token-level supervision from a stronger teacher. Vanilla OPD treats all teacher signals equally, assuming that...
arXiv:2601. 07155v3 Announce Type: replace-cross Abstract: Knowledge distillation (KD) is a widely adopted technique for transferring knowledge from large language models to smaller student models; however, conventional supervised KD often suffers from a distribution mismatch between training and inference.
arXiv:2608. 11698v1 Announce Type: cross Abstract: On-policy distillation (OPD) trains a student on its own trajectories under dense token-level supervision from a teacher.
arXiv:2602. 18037v2 Announce Type: replace-cross Abstract: Reinforcement Learning from Human Feedback (RLHF) or Verifiable Rewards (RLVR) are two key steps in the post-training of modern Language Models (LMs).
arXiv:2608. 09836v1 Announce Type: new Abstract: On-policy distillation (OPD) has emerged as a core component of modern LLM post-training pipelines, yet we reveal a failure mode: degenerate agreement, where students exploit repetitive loops to achieve near-perfect token agreement with the teacher despite globally flawed responses.
Reinforcement learning with verifiable rewards (RLVR) is a powerful recipe for improving language-model reasoning, but it is expensive to repeat on every new strong model because the target model must generate many rollouts during training. As models scale, post-training itself becomes a bottleneck.
arXiv:2609.39275v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own generated prefixes with token-level teacher feedback, but transmitting or storing the teacher'...
The paper introduces VISTA, a method that enhances on‑policy self‑distillation (OPSD) by adapting the teacher model toward the student’s distribution using outcome‑verified rollouts. VISTA keeps the standard OPSD student update but selectively adjusts the teacher only on the top‑k positions with the largest teacher‑student KL divergence, without adding new sampling or reward objectives. Experiments on AIME24, AIME25, and HMMT25 with Qwen3 models show that VISTA outperforms OPSD across all scales, improving Avg@12 by up to 2.1 points.
arXiv:2607. 05394v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is a powerful recipe for improving language-model reasoning, but it is expensive to repeat on every new strong model because the target model must generate many rollouts during training.