Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO

• URL: http://arxiv.org/abs/2505.11595v4
• Date: Wed, 01 Oct 2025 01:55:06 GMT
• Title: Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO
• Authors: Peter Chen, Xiaopeng Li, Ziniu Li, Xi Chen, Tianyi Lin,
• Abstract summary: Group Relative Policy Optimization fails to update a policy when all responses within a group are incorrect.<n>This limitation underscores a key gap between artificial and human intelligence.<n>We introduce a simple framework that mitigates the all-negative-sample issue by incorporating response diversity within groups.
• Score: 22.00487909203855
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning (RL) has proven effective in strengthening the reasoning capabilities of large language models (LLMs). A widely adopted method, Group Relative Policy Optimization (GRPO), has shown strong empirical results in training DeepSeek-R1. However, GRPO fails to update the policy when all responses within a group are incorrect (i.e., \emph{all-negative-sample} groups). This limitation underscores a key gap between artificial and human intelligence: unlike humans, who can learn from mistakes, GRPO discards these signals. Our first contribution is to introduce a simple framework that mitigates the all-negative-sample issue by incorporating response diversity within groups using a \textit{step-wise} judge model, which can be either directly trained or adapted from existing LLMs. We prove that this diversification can accelerate GRPO's learning dynamics in a simplified setting. We also empirically validate the proposed stepwise guided policy optimization (SGPO) method, demonstrating consistent gains across model sizes (7B, 14B, 32B) in offline and online training on 9 benchmarks, including base and distilled variants. Our results highlight two advantages: (i) SGPO surpasses GRPO, especially in the early and mid-training stages where all-negative-sample groups are prevalent; and (ii) SGPO does not require judge models to generate correct answers, differentiating it from knowledge distillation methods.

Related papers

• 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)
• 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)
• Rewarding the Unlikely: Lifting GRPO Beyond Distribution Sharpening [36.81125165911328]
  Reinforcement learning is emerging as a primary driver for improving language model reasoning capabilities.<n>We investigate whether current reinforcement learning algorithms merely sharpen the base model's distribution around problems it can already solve.<n>We show that unlikeliness reward mitigates rank bias and improves pass@$N$ across a large range of $N$ in both synthetic and real theorem proving settings.
  arXiv  Detail & Related papers  (2025-06-03T01:15:15Z)
• Reinforcing Video Reasoning with Focused Thinking [65.85683941058916]
  We propose TW-GRPO, a novel framework that enhances visual reasoning with focused thinking and dense reward granularity.<n>Specifically, we employ a token weighting mechanism that prioritizes tokens with high informational density.<n>We also reformulate RL training by shifting from single-choice to multi-choice QA tasks.
  arXiv  Detail & Related papers  (2025-05-30T15:42:19Z)
• On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization [52.76330545825083]
  Reinforcement learning (RL) has become popular in enhancing the reasoning capabilities of large language models (LLMs)<n>We identify a previously unrecognized phenomenon we term Lazy Likelihood Displacement (LLD), wherein the likelihood of correct responses marginally increases or even decreases during training.<n>We develop a method called NTHR, which downweights penalties on tokens contributing to the LLD. Unlike prior DPO-based approaches, NTHR takes advantage of GRPO's group-based structure, using correct responses as anchors to identify influential tokens.
  arXiv  Detail & Related papers  (2025-05-24T18:58:51Z)
• DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data [65.09939942413651]
  We propose a principled extension to GRPO that addresses inter-group imbalance with two key innovations.<n> Domain-aware reward scaling counteracts frequency bias by reweighting optimization based on domain prevalence.<n>Difficulty-aware reward scaling leverages prompt-level self-consistency to identify and prioritize uncertain prompts that offer greater learning value.
  arXiv  Detail & Related papers  (2025-05-21T03:43:29Z)
• DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization [50.91849555841057]
  Group Relative Policy Optimization is a reinforcement learning method for large reasoning models (LRMs)<n>We introduce a new Discriminative Constrained Optimization framework for reinforcing LRMs, grounded in the principle of discriminative learning.<n>DisCO significantly outperforms GRPO and its improved variants such as DAPO, achieving average gains of 7% over GRPO and 6% over DAPO.
  arXiv  Detail & Related papers  (2025-05-18T11:08:32Z)
• SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM [18.275547804539016]
  Two-Staged history-Resampling Policy optimization surpasses the performance of DeepSeek-R1-Zero-32B on the AIME24 and LiveCodeBench benchmarks.<n>We introduce two key methodological innovations: (1) a two-stage cross-domain training paradigm designed to balance the development of mathematical reasoning and coding proficiency, and (2) History Resampling (HR), a technique to address ineffective samples.
  arXiv  Detail & Related papers  (2025-04-19T13:06:03Z)
• A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce [68.99924691391048]
  We revisit GRPO from a reinforce-like algorithm perspective and analyze its core components.<n>We find that a simple rejection sampling baseline, RAFT, yields competitive performance than GRPO and PPO.<n>Motivated by this insight, we propose Reinforce-Rej, a minimal extension of policy gradient that filters both entirely incorrect and entirely correct samples.
  arXiv  Detail & Related papers  (2025-04-15T16:15:02Z)
• GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning [17.544255491384046]
  We propose a minimalist RL approach termed Group Policy Gradient (GPG)<n>Unlike conventional methods, GPG directly optimize the original RL objective, thus obviating the need for surrogate loss functions.<n>Our approach achieves superior performance without relying on auxiliary techniques or adjustments.
  arXiv  Detail & Related papers  (2025-04-03T12:53:41Z)
• Optimizing Safe and Aligned Language Generation: A Multi-Objective GRPO Approach [2.8626097661711394]
  Reinforcement Learning from Human Feedback has achieved notable success in steering models, but is complex and can be unstable.<n>Recent approaches such as Direct Preference Optimization (DPO) simplify preference-based fine-tuning but may introduce bias or trade-off certain objectives.<n>We propose a Group Relative Policy Optimization framework with a multi-label reward regression model to achieve safe and aligned language generation.
  arXiv  Detail & Related papers  (2025-03-26T05:50:33Z)
• Group Robust Preference Optimization in Reward-free RLHF [23.622835830345725]
  We propose a novel Group Robust Preference Optimization (GRPO) method to align large language models to individual groups' preferences robustly. To achieve this, GRPO adaptively and sequentially weights the importance of different groups, prioritizing groups with worse cumulative loss. We significantly improved performance for the worst-performing groups, reduced loss imbalances across groups, and improved probability accuracies.
  arXiv  Detail & Related papers  (2024-05-30T17:50:04Z)
• Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning [55.96599486604344]
  We introduce an approach aimed at enhancing the reasoning capabilities of Large Language Models (LLMs) through an iterative preference learning process. We use Monte Carlo Tree Search (MCTS) to iteratively collect preference data, utilizing its look-ahead ability to break down instance-level rewards into more granular step-level signals. The proposed algorithm employs Direct Preference Optimization (DPO) to update the LLM policy using this newly generated step-level preference data.
  arXiv  Detail & Related papers  (2024-05-01T11:10:24Z)
• REBEL: Reinforcement Learning via Regressing Relative Rewards [59.68420022466047]
  We propose REBEL, a minimalist RL algorithm for the era of generative models.<n>In theory, we prove that fundamental RL algorithms like Natural Policy Gradient can be seen as variants of REBEL.<n>We find that REBEL provides a unified approach to language modeling and image generation with stronger or similar performance as PPO and DPO.
  arXiv  Detail & Related papers  (2024-04-25T17:20:45Z)
• Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data [102.16105233826917]
  Learning from preference labels plays a crucial role in fine-tuning large language models. There are several distinct approaches for preference fine-tuning, including supervised learning, on-policy reinforcement learning (RL), and contrastive learning.
  arXiv  Detail & Related papers  (2024-04-22T17:20:18Z)
• Improving Generalization of Alignment with Human Preferences through Group Invariant Learning [56.19242260613749]
  Reinforcement Learning from Human Feedback (RLHF) enables the generation of responses more aligned with human preferences. Previous work shows that Reinforcement Learning (RL) often exploits shortcuts to attain high rewards and overlooks challenging samples. We propose a novel approach that can learn a consistent policy via RL across various data groups or domains.
  arXiv  Detail & Related papers  (2023-10-18T13:54:15Z)

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.