arXiv:2607. 28026v1 Announce Type: new Abstract: Recent advances in post-training Large Language Models (LLMs) increasingly rely on Reinforcement Learning with Verifiable Rewards (RLVR) or On-Policy Self-Distillation (OPSD).
Recent advances in post-training Large Language Models (LLMs) increasingly rely on Reinforcement Learning with Verifiable Rewards (RLVR) or On-Policy Self-Distillation (OPSD). While OPSD provides dense, logit-level supervision, it inherently suffers from exposure bias due to the privileged information of the self-teacher.
arXiv:2607. 28076v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is effective for training large language model agents.
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.
arXiv:2607. 14614v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) commonly uses entropy for advantage shaping.
arXiv:2608.21830v1 Announce Type: new Abstract: Graphical User Interface (GUI) agents powered by Multimodal Large Language Models (MLLMs) have shown strong potential for automating tasks across diver...
arXiv:2605.29089v2 Announce Type: replace-cross Abstract: Recent reinforcement learning (RL) post-training approaches primarily optimize the final output policy using sparse outcome-level rewards, wh...
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:2606. 09091v1 Announce Type: new Abstract: On-policy distillation (OPD) has recently emerged as an important post-training paradigm.
arXiv:2606. 05152v1 Announce Type: cross Abstract: Reasoning models have advanced rapidly, but the dominant reinforcement learning from verifiable rewards (RLVR) recipe remains surprisingly narrow: sample many responses and reward each with a single bit indicating whether the final answer is correct.
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.
arXiv:2606. 07000v1 Announce Type: new Abstract: Recent post-training methods, particularly Reinforcement Learning with Verifiable Rewards (RLVR), have significantly enhanced the reasoning ability of Large Vision-Language Models (LVLMs).
arXiv:2605.06387v4 Announce Type: replace-cross Abstract: On-policy distillation (OPD) trains a student on its own trajectories with token-level teacher feedback and often outperforms off-policy dist...