Difficulty-Estimated Policy Optimization

• URL: http://arxiv.org/abs/2602.06375v1
• Date: Fri, 06 Feb 2026 04:12:23 GMT
• Title: Difficulty-Estimated Policy Optimization
• Authors: Yu Zhao, Fan Jiang, Tianle Liu, Bo Zeng, Yu Liu, Longyue Wang, Weihua Luo,
• Abstract summary: We propose Difficulty-Estimated Policy Optimization (DEPO), a novel framework designed to optimize the efficiency and robustness of reasoning alignment.<n>Our approach significantly lowers the computational barrier for training high-performance reasoning models, offering a more sustainable path for reasoning scaling.
• Score: 38.86673795561421
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in Large Reasoning Models (LRMs), exemplified by DeepSeek-R1, have underscored the potential of scaling inference-time compute through Group Relative Policy Optimization (GRPO). However, GRPO frequently suffers from gradient signal attenuation when encountering problems that are either too trivial or overly complex. In these scenarios, the disappearance of inter-group advantages makes the gradient signal susceptible to noise, thereby jeopardizing convergence stability. While variants like DAPO attempt to rectify gradient vanishing, they do not alleviate the substantial computational overhead incurred by exhaustive rollouts on low-utility samples. In this paper, we propose Difficulty-Estimated Policy Optimization (DEPO), a novel framework designed to optimize the efficiency and robustness of reasoning alignment. DEPO integrates an online Difficulty Estimator that dynamically assesses and filters training data before the rollout phase. This mechanism ensures that computational resources are prioritized for samples with high learning potential. Empirical results demonstrate that DEPO achieves up to a 2x reduction in rollout costs without compromising model performance. Our approach significantly lowers the computational barrier for training high-performance reasoning models, offering a more sustainable path for reasoning scaling. Code and data will be released upon acceptance.

Related papers

• 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)
• Not All Preferences Are Created Equal: Stability-Aware and Gradient-Efficient Alignment for Reasoning Models [52.48582333951919]
  We propose a dynamic framework designed to enhance alignment reliability by maximizing the Signal-to-Noise Ratio of policy updates.<n>SAGE (Stability-Aware Gradient Efficiency) integrates a coarse-grained curriculum mechanism that refreshes candidate pools based on model competence.<n> Experiments on multiple mathematical reasoning benchmarks demonstrate that SAGE significantly accelerates convergence and outperforms static baselines.
  arXiv  Detail & Related papers  (2026-02-01T12:56:10Z)
• DaGRPO: Rectifying Gradient Conflict in Reasoning via Distinctiveness-Aware Group Relative Policy Optimization [20.66452395111739]
  We propose Distinctiveness-aware Group Relative Policy Optimization (DaGRPO)<n>DaGRPO incorporates two core mechanisms: (1) Sequence-level Gradient Rectification, which utilizes fine-grained scoring to dynamically mask sample pairs with low distinctiveness; and (2) Off-policy Data Augmentation, which introduces high-quality anchors to recover training signals for challenging tasks.<n>In-depth analysis confirms that DaGRPO effectively mitigates gradient explosion and accelerates the emergence of long-chain reasoning capabilities.
  arXiv  Detail & Related papers  (2025-12-06T07:51:36Z)
• Empirical Comparison of Forgetting Mechanisms for UCB-based Algorithms on a Data-Driven Simulation Platform [0.16921396880325776]
  This paper introduces and evaluates FDSW-UCB, a novel dual-view algorithm that integrates a discount-based long-term perspective with a sliding-window-based short-term view.<n>It achieves superior performance in dynamic settings, highlighting that the ensemble strategy itself is a decisive factor for success.
  arXiv  Detail & Related papers  (2025-11-24T15:52:02Z)
• Beyond Reward Margin: Rethinking and Resolving Likelihood Displacement in Diffusion Models via Video Generation [6.597818816347323]
  Direct Preference Optimization aims to align generative outputs with human preferences by distinguishing between chosen and rejected samples.<n>A critical limitation of DPO is likelihood displacement, where the probabilities of chosen samples paradoxically decrease during training.<n>We introduce a novel solution named Policy-Guided DPO, combining Adaptive Rejection Scaling (ARS) and Implicit Preference Regularization (IPR)<n>Experiments show that PG-DPO outperforms existing methods in both quantitative metrics and qualitative evaluations.
  arXiv  Detail & Related papers  (2025-11-24T12:37:49Z)
• G$^2$RPO: Granular GRPO for Precise Reward in Flow Models [74.21206048155669]
  We propose a novel Granular-GRPO (G$2$RPO) framework that achieves precise and comprehensive reward assessments of sampling directions.<n>We introduce a Multi-Granularity Advantage Integration module that aggregates advantages computed at multiple diffusion scales.<n>Our G$2$RPO significantly outperforms existing flow-based GRPO baselines.
  arXiv  Detail & Related papers  (2025-10-02T12:57:12Z)
• Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning [77.92320830700797]
  Reinforcement Learning has played a central role in enabling reasoning capabilities of Large Language Models.<n>We propose a tractable computational framework that tracks and leverages curvature information during policy updates.<n>The algorithm, Curvature-Aware Policy Optimization (CAPO), identifies samples that contribute to unstable updates and masks them out.
  arXiv  Detail & Related papers  (2025-10-01T12:29:32Z)
• CART-based Synthetic Tabular Data Generation for Imbalanced Regression [1.342834401139078]
  We propose adapting an existing CART-based synthetic data generation method, tailoring it for imbalanced regression.<n>The new method integrates relevance and density-based mechanisms to guide sampling in sparse regions of the target space.<n>Our experimental study focuses on the prediction of extreme target values across benchmark datasets.
  arXiv  Detail & Related papers  (2025-06-03T12:42:20Z)
• 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)
• Uncertainty-Penalized Direct Preference Optimization [52.387088396044206]
  We develop a pessimistic framework for DPO by introducing preference uncertainty penalization schemes. The penalization serves as a correction to the loss which attenuates the loss gradient for uncertain samples. We show improved overall performance compared to vanilla DPO, as well as better completions on prompts from high-uncertainty chosen/rejected responses.
  arXiv  Detail & Related papers  (2024-10-26T14:24:37Z)

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.