arXiv:2605.10194v2 Announce Type: replace Abstract: On-policy self-distillation (OPSD) uses a model as its own teacher under privileged context, providing token-level supervision on the model's own r...
arXiv:2606. 11709v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) provides dense, token-level supervision for reasoning models by aligning a model's own distribution with the distribution it produces under privileged context, typically a verified solution.
On-policy self-distillation (OPSD) provides dense, token-level supervision for reasoning models by aligning a model's own distribution with the distribution it produces under privileged context, typically a verified solution. However, we show that the learning signal drawn from this distributional gap concentrates on style tokens rather than task-bearing ones, as the hinted model tends to produce more direct, shorter outputs.
arXiv:2607. 15161v1 Announce Type: new Abstract: On-policy distillation is an alternative post-training method in reinforcement learning that alleviates the constraints imposed by reward models by providing token-level supervision from a teacher model.
arXiv:2602. 02244v3 Announce Type: replace Abstract: The standard post-training recipe for large reasoning models, supervised fine-tuning followed by reinforcement learning (SFT-then-RL), may limit the benefits of the RL stage: while SFT imitates expert demonstrations, it often causes overconfidence and reduces generation diversity, leaving RL with a narrowed solution space to explore.
arXiv:2607. 18955v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models on tasks such as mathematical reasoning and code generation.
SIPO (Self‑Instructing Policy Optimization) unifies reinforcement learning with on‑policy self‑distillation by using a contrastive self‑teacher to generate token‑level credit signals. The method samples multiple rollouts per prompt, pairs each with a reference answer and its mistakes, and uses the difference in teacher log‑probabilities to provide dense feedback while still respecting the overall task reward. Experiments on reasoning and code‑generation benchmarks show that SIPO outperforms both RLVR and OPSD baselines without requiring an external teacher or extra generation steps.
The paper investigates why self‑distillation can sometimes worsen the reasoning abilities of large language models (LLMs). It finds that the process suppresses the model’s epistemic verbalization—its expression of uncertainty—leading to shorter but less accurate responses in mathematical reasoning tasks. Experiments on several LLMs show performance drops of up to 40%, especially on out‑of‑distribution problems where uncertainty expression is beneficial.
arXiv:2610.17734v1 Announce Type: cross Abstract: Exploration bounds learning efficiency in reinforcement learning with verifiable rewards (RLVR). Current methods explore mostly through independent s...
arXiv:2610.09665v1 Announce Type: new Abstract: On-policy post-training can improve large language models by learning from their own trajectories, but requires costly rollout generation. We ask wheth...
VASPO introduces a new integration of self-distillation and PPO by leveraging privileged value estimation to guide language model training. The method uses a self-teacher and a critic that both evaluate the same privileged information on student-generated prefixes, allowing the critic to compute token-level PPO advantages from predicted continuation returns while the teacher modulates positive advantages via bounded probability ratios. Experiments on six mathematical reasoning benchmarks show that VASPO improves mean accuracy over standard PPO by 2.59 and 1.81 percentage points on Qwen3-4B and OLMo3-7B, respectively, and achieves the highest mean accuracy among evaluated methods on Knights and Knaves.
arXiv:2609.37041v1 Announce Type: cross Abstract: Self-Distillation Fine-Tuning (SDFT) enables a language model to act as its own teacher: by conditioning on a demonstration, the model produces an im...