# Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training

arXiv: https://arxiv.org/abs/2605.12483 · HTML: https://mlsanity.com/paper/2605.12483/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 34 of its 46 references that are in the map.
- First posted on arXiv 12 May 2026.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)
- Knowledge distillation / [On-policy and self-distillation for LLMs](https://mlsanity.com/distill/on-policy-and-self-distillation-for-llms/)

## Builds on (most cited first, 30 of 34)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://mlsanity.com/paper/2409.12122/) (2024)
- [Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe](https://mlsanity.com/paper/2604.13016/) (2026)
- [Specializing Smaller Language Models towards Multi-Step Reasoning](https://mlsanity.com/paper/2301.12726/) (2023)
- [Self-Distillation Enables Continual Learning](https://mlsanity.com/paper/2601.19897/) (2026)
- [MiMo-V2-Flash Technical Report](https://mlsanity.com/paper/2601.02780/) (2026)
- [On-Policy Context Distillation for Language Models](https://mlsanity.com/paper/2602.12275/) (2026)
- [A Survey of On-Policy Distillation for Large Language Models](https://mlsanity.com/paper/2604.00626/) (2026)
- [Self-Distilled RLVR](https://mlsanity.com/paper/2604.03128/) (2026)
- [Explanations from Large Language Models Make Small Reasoners Better](https://mlsanity.com/paper/2210.06726/) (2022)
- [TIP: Token Importance in On-Policy Distillation](https://mlsanity.com/paper/2604.14084/) (2026)
- [Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents](https://mlsanity.com/paper/2604.10674/) (2026)
- [Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision](https://mlsanity.com/paper/2604.12002/) (2026)
- [Black-Box On-Policy Distillation of Large Language Models](https://mlsanity.com/paper/2511.10643/) (2025)
- [CRISP: Compressed Reasoning via Iterative Self-Policy Distillation](https://mlsanity.com/paper/2603.05433/) (2026)
- [Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe](https://mlsanity.com/paper/2605.03677/) (2026)
- [TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents](https://mlsanity.com/paper/2604.24005/) (2026)
- [Reinforcement-aware Knowledge Distillation for LLM Reasoning](https://mlsanity.com/paper/2602.22495/) (2026)
- [Flow-OPD: On-Policy Distillation for Flow Matching Models](https://mlsanity.com/paper/2605.08063/) (2026)
- [Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation](https://mlsanity.com/paper/2604.13010/) (2026)
- [PACED: Distillation and On-Policy Self-Distillation at the Frontier of Student Competence](https://mlsanity.com/paper/2603.11178/) (2026)
- [Rubric-based On-policy Distillation](https://mlsanity.com/paper/2605.07396/) (2026)
- [Learn Hard Problems During RL with Reference Guided Fine-tuning](https://mlsanity.com/paper/2603.01223/) (2026)

## Built on by (most cited first, 11 of 11)

- [Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR](https://mlsanity.com/paper/2609.04108/) (2026)
- [TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning](https://mlsanity.com/paper/2606.32017/) (2026)
- [RISE: Recursive Improvement via Self-Extrapolating Policy Distillation](https://mlsanity.com/paper/2609.05295/) (2026)
- [Simple-OPD: Demystifying Warm-up for On-policy Distillation](https://mlsanity.com/paper/2608.06802/) (2026)
- [Same Question, Different Answer? Measuring and Mitigating Prompt Privilege for Equitable AI Access](https://mlsanity.com/paper/2608.08942/) (2026)
- [Scope3Trace: Evidence-Based Identification and Extraction of Scope 3 GHG Emissions from Sustainability Reports](https://mlsanity.com/paper/2607.17122/) (2026)
- [Hybrid-Policy Self-Editing for Composable Unstructured Knowledge Editing](https://mlsanity.com/paper/2608.11660/) (2026)
- [Expected Reasoning-Step Return Unifies On-Policy Learning from Rewards and Teachers](https://mlsanity.com/paper/2609.32674/) (2026)
- [UOPD: Uncertainty-Aware Intervention for On-Policy Distillation of Multi-Turn Agents](https://mlsanity.com/paper/2609.34036/) (2026)
- [Transfer-Stratified On-Policy Distillation for RL-Improved Reasoning Teachers](https://mlsanity.com/paper/2610.05974/) (2026)
- [Composing What Each Teacher Learned: Multi-Teacher On-Policy Distillation through Teacher-Relative Shifts](https://mlsanity.com/paper/2610.10460/) (2026)

## Abstract (arXiv)

In settings where labeled verifiable training data is the binding constraint, each checked example should be allocated to the model and reward density where it is most informative. We identify a reward-density principle: sparse sequence-level reward is most useful on models that can explore and discover better behavior, while dense token-level teacher supervision is better suited for compressing that behavior into a smaller deployment model; accordingly, scarce labeled data should be used upstream on the strongest available teacher, then transferred downstream as dense supervision. We evaluate this rule through a four-stage workflow:teacher RL, forward-KL warmup, on-policy distillation, optional post-bridge student RL on verifiable math and code generation with Qwen3, Llama, and Qwen2.5 models. At fixed Qwen3-1.7B deployment-student size, an RL-improved 8B teacher distilled through the dense bridge outperforms direct GRPO on the same student (79.3% vs. 75.9% on MATH; 25.2% vs. 19.8% on AIME~2024), while transfer from the same teacher before RL underperforms. A component ablation confirms that each stage is load-bearing: the RL-improved teacher adds 7.8 absolute points on MATH over a raw teacher of the same size, the forward-KL warmup adds 1.7, and on-policy distillation adds 3.3. The teacher-quality ordering: raw-teacher transfer < direct GRPO < RL-teacher transfer, replicates on Llama-3.1-8B-Instruct with a Llama-3.3-70B-Instruct teacher and on Qwen2.5-7B-Instruct for code generation with a Qwen2.5-32B-Instruct teacher. The operational lesson is to avoid spending scarce labeled data on the least prepared policy: use sparse reward for teacher-side discovery, dense transfer for student compression, and student-side sparse reward only after the bridge. The OPD implementation used in our experiments is available at https://github.com/HJSang/OPSDOnPolicyDistillation.