arXiv AI
Jul 21
Distilled Reinforcement Learning for LLM Post-training
arXiv:2607. 17247v1 Announce Type: cross Abstract: Large language model (LLM) post-training is essential for improving reasoning, adaptation, and alignment.
RL Starts before RL: On Policy Distillation for Better Reinforcement Learning
The paper investigates on‑policy distillation (OPD) as a preparatory step for reinforcement learning (RL). It shows that students initialized with OPD achieve higher final RL performance than those trained directly with RL or with supervised fine‑tuning followed by RL, even when OPD offers little immediate accuracy gain. The study also finds that the choice of distillation objective (reverse‑KL vs forward‑KL) and the source of trajectories influence OPD’s effectiveness at different stages of RL training.
Related stories
arXiv AI
Jun 19
Reinforcement-aware Knowledge Distillation for LLM Reasoning
arXiv:2602. 22495v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference cost of such models motivates distillation into smaller students.
arXiv AI
1d ago
STEPS: Selective On-Policy Self-Distillation for Reasoning
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 AI
Aug 26
OPDSearch+: On-Policy Distillation with RL Refinement for Search-Augmented Reasoning
OPDSearch+ introduces a two‑stage distillation framework for search‑augmented reasoning that eliminates the need for task‑specific teacher fine‑tuning. In the first stage, a frozen off‑the‑shelf instruct model guides a student through live search interactions using a per‑position forward KL objective, transferring reasoning decomposition and evidence integration skills. The second stage refines this student with reinforcement learning, achieving performance surpassing RL alone and outperforming all prior 3B‑parameter baselines on seven QA benchmarks, including 13.1% improvement on HotpotQA and 8.5% on 2WikiMultihopQA.
arXiv Machine Learning
Jul 17
On-Policy Delta Distillation
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 AI
1d ago
From Imitation to Reward Discovery: On-Policy Warmup for Agentic RL
The paper introduces On‑Policy Warmup (OPW), a teacher‑guided training stage where a student agent learns from a teacher on its own interaction trajectories before switching to reinforcement learning with verifiable rewards (RLVR). OPW differs from traditional imitation by focusing on states generated by the student’s own decisions, including imperfect actions and recovery situations. The authors provide a theoretical link between on‑policy reverse‑KL distillation and trajectory‑level distribution matching, showing that, under a competent teacher and low distillation loss, OPW can lower bound initial verifier success and reduce reward‑discovery complexity, thereby accelerating RLVR performance.
Hugging Face Trending Papers
Aug 25
OPDSearch+: On-Policy Distillation with RL Refinement for Search-Augmented Reasoning
Search-augmented reasoning remains difficult for small language models. On-policy distillation (OPD) from trained teachers offers a promising direction, but suffers from two issues: (1) high-quality m...
arXiv AI
Sep 4
Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR
The paper investigates how on-policy distillation (OPD) and reinforcement learning with verifiable rewards (RLVR) can be combined for post‑training reasoning in large language models. It shows that a two‑stage approach—first applying OPD, then RL—outperforms single‑signal methods and other joint baselines on logic and math reasoning benchmarks. The authors explain this advantage through pass@k analysis, learning dynamics, and parameter updates, concluding that OPD expands solution coverage while RL sharpens performance within that support, and that the OPD validation score is the key trigger for switching to RL.
Hugging Face Trending Papers
Jul 6
Weak-to-Strong Generalization via Direct On-Policy Distillation
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 Computer Vision
1d ago
ReDiF: Resource-Efficient Few-Step Diffusion Distillation via Reinforcement Learning
arXiv:2512.22802v2 Announce Type: replace-cross Abstract: Step distillation accelerates diffusion sampling by training a few-step student to imitate a many-step teacher, but distillation itself remai...
arXiv AI
Jun 2
Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation
arXiv:2605. 09253v2 Announce Type: replace-cross Abstract: While recent work in Reinforcement Learning with Verifiable Rewards (RLVR) has shown that a small subset of critical tokens disproportionately drives reasoning gains, an analogous token-level understanding of On-Policy Distillation (OPD) remains largely unexplored.
arXiv AI
Jul 31
ATOD: Annealed Turn-Aware On-Policy Distillation for Multi-Turn Agentic Tasks
arXiv:2606. 27814v4 Announce Type: replace Abstract: Training small language-model agents for long-horizon interactive tasks requires both fast imitation and reward-driven improvement.