Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing

• URL: http://arxiv.org/abs/2604.02288v1
• Date: Thu, 02 Apr 2026 17:29:18 GMT
• Title: Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
• Abstract summary: Self-Distillation Policy Optimization (SDPO) addresses this by providing denser, more targeted logit-level supervision.<n>We propose Sample-Routed Policy Optimization (SRPO)<n>SRPO routes correct samples to GRPO's reward-aligned reinforcement and failed samples to SDPO's targeted logit-level correction.
• Score: 79.88256756334327
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training large language models. While Group Relative Policy Optimization (GRPO) is widely adopted, its coarse credit assignment uniformly penalizes failed rollouts, lacking the token-level focus needed to efficiently address specific deviations. Self-Distillation Policy Optimization (SDPO) addresses this by providing denser, more targeted logit-level supervision that facilitates rapid early improvement, yet it frequently collapses during prolonged training. We trace this late-stage instability to two intrinsic flaws: self-distillation on already-correct samples introduces optimization ambiguity, and the self-teacher's signal reliability progressively degrades. To resolve these issues, we propose Sample-Routed Policy Optimization (SRPO), a unified on-policy framework that routes correct samples to GRPO's reward-aligned reinforcement and failed samples to SDPO's targeted logit-level correction. SRPO further incorporates an entropy-aware dynamic weighting mechanism to suppress high-entropy, unreliable distillation targets while emphasizing confident ones. Evaluated across five benchmarks and two model scales, SRPO achieves both the rapid early improvement of SDPO and the long-horizon stability of GRPO. It consistently surpasses the peak performance of both baselines, raising the five-benchmark average on Qwen3-8B by 3.4% over GRPO and 6.3% over SDPO, while simultaneously yielding moderate response lengths and lowering per-step compute cost by up to 17.2%.

Related papers

• When Denser Credit Is Not Enough: Evidence-Calibrated Policy Optimization for Long-Horizon LLM Agent Training [8.367896852036699]
  We propose Evidence-Calibrated Policy Optimization (ECPO), a critic-free policy optimization algorithm that calibrates step-level credit before policy updates.<n>ECPO consistently outperforms strong baselines, improving GiGPO by +5.2/+7.3 success points on ALFWorld/WebShop with Qwen2.5-1.5B while adding only 0.1% additional advantage-computation overhead.
  arXiv  Detail & Related papers  (2026-06-04T08:54:09Z)
• Ratio-Variance Regularized Policy Optimization [64.95520246570446]
  We show that explicitly constraining the policy ratio variance provides a principled local approximation to trust-region constraints.<n>We introduce $bf R2bf VPO$ (Ratio-Variance Regularized Policy Optimization), which implements this constraint via a primal-dual optimization framework.
  arXiv  Detail & Related papers  (2026-05-26T09:53:42Z)
• Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation [13.272542054938258]
  We introduce the Advantage Collapse Rate (ACR), the first metric quantifying the proportion of training batches with ineffective gradients.<n>We then propose Adaptive Virtual Sample Policy Optimization (AVSPO), a lightweight extension of GRPO that injects virtual reward samples.<n>AVSPO reduces advantage collapse by 58-63% relative to GRPO and yields consistent accuracy gains of 4-6 percentage points across all model scales.
  arXiv  Detail & Related papers  (2026-05-20T12:57:37Z)
• Improving Search Agent with One Line of Code [68.58667107354253]
  Tool-based Agentic Reinforcement Learning (TARL) has emerged as a promising paradigm for training search agents to interact with external tools.<n>We propose textbfSearch textbfAgent textbfPolicy textbfOptimization (textbfSAPO), which stabilizes training via a conditional token-level KL constraint.
  arXiv  Detail & Related papers  (2026-03-10T04:07:39Z)
• Unbiased Dynamic Pruning for Efficient Group-Based Policy Optimization [60.87651283510059]
  Group Relative Policy Optimization (GRPO) effectively scales LLM reasoning but incurs prohibitive computational costs.<n>We propose Dynamic Pruning Policy Optimization (DPPO), a framework that enables dynamic pruning while preserving unbiased gradient estimation.<n>To mitigate the data sparsity induced by pruning, we introduce Dense Prompt Packing, a window-based greedy strategy.
  arXiv  Detail & Related papers  (2026-03-04T14:48:53Z)
• WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning [67.45237332694025]
  Group Relative Policy Optimization is effective for training language models on complex reasoning.<n>We propose Weakly Supervised GRPO, which improves rollout efficiency by converting terminal rewards into correctness-aware guidance.
  arXiv  Detail & Related papers  (2026-02-19T02:43:35Z)
• iGRPO: Self-Feedback-Driven LLM Reasoning [88.83313431248473]
  Large Language Models (LLMs) have shown promise in solving complex mathematical problems, yet they still fall short of producing accurate and consistent solutions.<n>We introduce Iterative Group Relative Policy Optimization (iGRPO), a two-stage extension of GRPO that adds dynamic self-conditioning through model-generated drafts.<n>Under matched rollout budgets, iGRPO consistently outperforms GRPO across base models.
  arXiv  Detail & Related papers  (2026-02-09T18:45:11Z)
• Back to Basics: Revisiting Exploration in Reinforcement Learning for LLM Reasoning via Generative Probabilities [10.235183326885794]
  Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an indispensable paradigm for enhancing reasoning in Large Language Models (LLMs)<n>We analyze this issue from the perspective of sampling probability dynamics, identifying that the standard objective disproportionately reinforces the highest-likelihood paths.<n>We propose a novel Advantage Re-weighting Mechanism (ARM) designed to equilibrate the confidence levels across all correct responses.
  arXiv  Detail & Related papers  (2026-02-05T04:06:55Z)
• PRPO: Aligning Process Reward with Outcome Reward in Policy Optimization [15.965340493880701]
  We introduce Process Relative Policy Optimization (PRPO), which combines outcome reliability with process-level guidance in a critic-free framework.<n>PRPO segments reasoning sequences based on semantic clues, normalizes PRM scores into token-level advantages, and aligns their distribution with outcome advantages.<n>On MATH500, PRPO improves Qwen2.5-Math-1.5B accuracy from 61.2% to 64.4% over GRPO using only eight rollouts and no value network.
  arXiv  Detail & Related papers  (2026-01-12T04:04:43Z)
• Anchoring Values in Temporal and Group Dimensions for Flow Matching Model Alignment [61.80228667422234]
  VGPO redefines value estimation across both temporal and group dimensions.<n>It transforms the sparse terminal reward into dense, process-aware value estimates.<n>It replaces standard group normalization with a novel process enhanced by absolute values to maintain a stable optimization signal.
  arXiv  Detail & Related papers  (2025-12-13T16:31:26Z)
• BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping [69.74252624161652]
  We propose BAlanced Policy Optimization with Adaptive Clipping (BAPO)<n>BAPO dynamically adjusts clipping bounds to adaptively re-balance positive and negative contributions, preserve entropy, and stabilize RL optimization.<n>On AIME 2024 and AIME 2025 benchmarks, our 7B BAPO model surpasses open-source counterparts such as SkyWork-OR1-7B.
  arXiv  Detail & Related papers  (2025-10-21T12:55:04Z)
• Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning [45.51804571136028]
  Reinforcement learning (RL) has become central to enhancing reasoning in large language models (LLMs)<n>We introduce Slow-Fast Policy Optimization (SFPO), a simple yet efficient framework to address these limitations via decomposing each step into three stages.<n>SFPO consistently improves stability, reduces rollouts, and accelerates convergence of reasoning RL training.
  arXiv  Detail & Related papers  (2025-10-05T07:22:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.