PAPO: Stabilizing Rubric Integration Training via Decoupled Advantage Normalization

• URL: http://arxiv.org/abs/2603.26535v3
• Date: Fri, 03 Apr 2026 07:00:08 GMT
• Title: PAPO: Stabilizing Rubric Integration Training via Decoupled Advantage Normalization
• Abstract summary: We propose Process-Aware Policy Optimization (PAPO) to address two limitations of existing reward designs.<n>PAPO integrates process-level evaluation into Group Relative Policy Optimization (GRPO) through decoupled advantage normalization.<n> Experiments across multiple model scales and six benchmarks demonstrate that PAPO consistently outperforms ORM.
• Score: 31.935482701047544
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose Process-Aware Policy Optimization (PAPO), a method that integrates process-level evaluation into Group Relative Policy Optimization (GRPO) through decoupled advantage normalization, to address two limitations of existing reward designs. Outcome reward models (ORM) evaluate only final-answer correctness, treating all correct responses identically regardless of reasoning quality, and gradually lose the advantage signal as groups become uniformly correct. Process reward models (PRM) offer richer supervision, but directly using PRM scores causes reward hacking, where models exploit verbosity to inflate scores while accuracy collapses. PAPO resolves both by composing the advantage from an outcome component Aout, derived from ORM and normalized over all responses, and a process component Aproc, derived from a rubric-based PRM and normalized exclusively among correct responses. This decoupled design ensures that Aout anchors training on correctness while Aproc differentiates reasoning quality without distorting the outcome signal. Experiments across multiple model scales and six benchmarks demonstrate that PAPO consistently outperforms ORM, reaching 51.3% vs.\ 46.3% on OlympiadBench while continuing to improve as ORM plateaus and declines.

Related papers

• PRO-Step: Step-level Process Reward Optimization for Retrieval-Augmented Generation [2.198430261120653]
  We introduce PRO-STEP: we train a generative PRM that evaluates logical validity and evidential grounding at each step.<n>Experiments on single and multi-hop QA datasets demonstrate that PRO-STEP achieves the best average EM and F1 across five benchmarks.
  arXiv  Detail & Related papers  (2026-08-31T14:34:10Z)
• TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning [52.67756371231985]
  Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models.<n>We introduce Tree Rollout Allocation for Contrastive Exploration (TRACE), a unified rollout allocation framework.<n>Technically, TRACE allocates rollout budget to both prompt roots and intermediate prefixes that are most likely to yield mixed terminal rewards.
  arXiv  Detail & Related papers  (2026-06-09T17:16:03Z)
• 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)
• Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing [79.88256756334327]
  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.
  arXiv  Detail & Related papers  (2026-04-02T17:29:18Z)
• When Right Meets Wrong: Bilateral Context Conditioning with Reward-Confidence Correction for GRPO [18.988527161000203]
  Group Relative Policy Optimization (GRPO) has emerged as an effective method for training reasoning models.<n>We present a contrastive reformulation of GRPO, showing that the GRPO objective implicitly maximizes the margin between the policy ratios of correct and incorrect samples.<n>We propose Bilateral Context Conditioning (BICC), a mechanism that allows the model to cross-reference successful and failed reasoning traces.
  arXiv  Detail & Related papers  (2026-03-13T16:25:02Z)
• LLM Reasoning with Process Rewards for Outcome-Guided Steps [7.3312414850609215]
  We introduce process reward models (PRMs) to score intermediate steps and provide denser supervision.<n>PRM scores are often imperfectly aligned with final correctness and can reward locally fluent reasoning that still ends in an incorrect answer.<n>We propose PROGRS, a framework that leverages PRMs while keeping outcome correctness dominant.
  arXiv  Detail & Related papers  (2026-02-08T06:38:20Z)
• 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)
• Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning [59.76691952347156]
  Reinforcement learning (RL) has emerged as a powerful framework for improving the reasoning capabilities of large language models (LLMs)<n>Most existing RL approaches rely on sparse outcome rewards, which fail to credit correct intermediate steps in partially successful solutions.<n>We propose Verifiable Prefix Policy Optimization (VPPO), which uses PRMs only to localize the first error during RL.
  arXiv  Detail & Related papers  (2026-01-26T21:38:20Z)
• 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)
• GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization [133.27496265096445]
  We show how to apply Group Relative Policy Optimization under multi-reward setting without examining its suitability.<n>We then introduce Group reward-Decoupled Normalization Policy Optimization (GDPO), a new policy optimization method to resolve these issues.<n>GDPO consistently outperforms GRPO, demonstrating its effectiveness and generalizability for multi-reward reinforcement learning optimization.
  arXiv  Detail & Related papers  (2026-01-08T18:59:24Z)
• Unified Generation and Self-Verification for Vision-Language Models via Advantage Decoupled Preference Optimization [48.078132893679744]
  We propose a unified reinforcement learning framework that jointly learns answer generation and self-verification within a single policy.<n>ADPO achieves up to +34.1% higher verification AUC and -53.5% lower inference time, with significant gains of +2.8%/+1.4% accuracy on MathVista/MMMU, +1.9 cIoU on ReasonSeg, and +1.7%/+1.0% step success rate on AndroidControl/GUI Odyssey.
  arXiv  Detail & Related papers  (2026-01-04T11:09:33Z)
• From Noisy Traces to Stable Gradients: Bias-Variance Optimized Preference Optimization for Aligning Large Reasoning Models [90.45197506653341]
  Large reasoning models generate intermediate reasoning traces before producing final answers.<n> aligning LRMs with human preferences, a crucial prerequisite for model deployment, remains underexplored.<n>A common workaround optimized a single sampled trajectory, which introduces substantial gradient variance from trace sampling.
  arXiv  Detail & Related papers  (2025-10-06T17:58:01Z)
• Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning [90.23629291067763]
  A promising approach for improving reasoning in large language models is to use process reward models (PRMs) PRMs provide feedback at each step of a multi-step reasoning trace, potentially improving credit assignment over outcome reward models (ORMs) To improve a base policy by running search against a PRM or using it as dense rewards for reinforcement learning (RL), we ask: "How should we design process rewards?" We theoretically characterize the set of good provers and our results show that optimizing process rewards from such provers improves exploration during test-time search and online RL.
  arXiv  Detail & Related papers  (2024-10-10T17:31:23Z)
• Prior Constraints-based Reward Model Training for Aligning Large Language Models [58.33118716810208]
  This paper proposes a Prior Constraints-based Reward Model (namely PCRM) training method to mitigate this problem. PCRM incorporates prior constraints, specifically, length ratio and cosine similarity between outputs of each comparison pair, during reward model training to regulate optimization magnitude and control score margins. Experimental results demonstrate that PCRM significantly improves alignment performance by effectively constraining reward score scaling.
  arXiv  Detail & Related papers  (2024-04-01T07:49:11Z)
• Pairwise Proximal Policy Optimization: Harnessing Relative Feedback for LLM Alignment [37.52249093928251]
  This paper proposes a new framework, reinforcement learning with relative feedback, and a novel trajectory-wise policy gradient algorithm. We show theoretically that P3O is invariant to equivalent rewards and avoids the complexity of PPO. Empirical evaluations demonstrate that P3O outperforms PPO in the KL-Reward trade-off and can align with human preferences as well as or better than prior methods.
  arXiv  Detail & Related papers  (2023-09-30T01:23:22Z)

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.