Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals

• URL: http://arxiv.org/abs/2605.22703v1
• Date: Thu, 21 May 2026 16:45:31 GMT
• Title: Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals
• Abstract summary: Near-boundary Rescue (NSR) is a minimal, plug-and-play modification that retains out-of-bound tokens to recover lost signals.<n>NSR substantially improves training stability and delivers consistent gains over strong baselines such as DAPO and GSPO.
• Score: 83.0127582612634
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a central paradigm for scaling LLM reasoning, yet its optimization often suffers from training instability and suboptimal convergence. Through a systematic dissection of clipping-based GRPO-style objectives, we identify the rigid clipping decision induced by hard clipping as a key practical bottleneck in the studied RLVR setups. Specifically, our analysis suggests that informative signals can lie in the near-boundary region just beyond the clipping threshold, and are therefore discarded by the standard hard-clipping rule. Notably, once this bottleneck is precisely identified, even simple stochastic perturbations at the boundary can recover meaningful performance gains. Building on this finding, we propose Near-boundary Stochastic Rescue (NSR), a minimal, plug-and-play modification that stochastically retains these slightly out-of-bound tokens to recover lost signals. While NSR, via stochastic sampling, can be interpreted as inducing an implicit gradient decay in expectation, our ablations reveal that its stochastic, boundary-local rescue mechanism is consistently more effective than deterministic gradient decay. Validated by extensive experiments across model sizes from 7B to 30B and both dense and MoE architectures, as a plug-and-play solution, NSR substantially improves training stability and delivers consistent gains over strong baselines such as DAPO and GSPO.

Related papers

• Stable-MM-R1: Anchoring Multimodal Reasoning Dynamics via Entropy-Guided Stratification [19.490862077232205]
  We propose a data-centric framework to stabilize Reinforcement Learning training.<n>We first introduce Potential-Aware Query Mining (PAQM), which filters data dynamically to focus on the "Distillation Zone"---samples with high potential for capability elicitation.<n>We present Hybrid Stratified Replay (HSR), a novel mechanism that restructures batches by stratifying rollouts based on Path Entropy, a rollout-level confidence proxy, and outcome reward.
  arXiv  Detail & Related papers  (2026-09-07T07:47:00Z)
• Local Epistemic Uncertainty Guided Active Sampling for Plug-and-play Diffusive Image Restoration [15.371827475537776]
  Local Epistemic Uncertainty Guided Active Sampling framework is developed.<n>It balances detail preservation and artifact suppression in the spatial domain.<n>It reduces sampling time with negligible memory overhead.
  arXiv  Detail & Related papers  (2026-08-07T09:00:20Z)
• Adaptive Iterative Hard Thresholding for Online High-dimensional Quantile Regression [1.0067421338825542]
  We propose an online sparse-regression framework that alternates subgradient updates with adaptively scheduled hard-thresholding steps.<n>We develop the theory for high-dimensional online quantile regression, a challenging setting in which the loss is nonsmooth.
  arXiv  Detail & Related papers  (2026-06-26T23:44:10Z)
• Next-Acceleration-Scale Prediction for Autoregressive MRI Reconstruction [52.32112533846212]
  MRI reconstruction is an inherently ill-posed inverse problem, since incomplete measurements admit many plausible solutions.<n>We address this limitation by moving reconstruction to discrete multi-scale latent space and posing it as autoregressive next-acceleration-scale prediction.<n>We show that our approach delivers improved reconstruction performance across diverse sampling patterns under extreme undersampling.
  arXiv  Detail & Related papers  (2026-05-19T04:40:50Z)
• Analytic Drift Resister for Non-Exemplar Continual Graph Learning [23.86709351309769]
  Non-Exemplar Continual Graph Learning (NECGL) seeks to eliminate the privacy risks intrinsic to rehearsal-based paradigms.<n>We propose Analytic Drift Resister (ADR), a novel and theoretically grounded NECGL framework.<n> ADR exploits iterative backpropagation to break free from the frozen pre-trained constraint.
  arXiv  Detail & Related papers  (2026-04-03T01:58:11Z)
• Variational Rectification Inference for Learning with Noisy Labels [74.85528327499662]
  We propose variational rectification inference (VRI) to formulate the adaptive rectification for loss functions.<n>VRI is constructed as a hierarchical Bayes by treating the rectifying vector as a latent variable.<n>By introducing the variational term in VRI, the conditional posterior is estimated accurately and avoids collapsing to a Dirac delta function.
  arXiv  Detail & Related papers  (2026-03-18T01:25:08Z)
• GTS: Inference-Time Scaling of Latent Reasoning with a Learnable Gaussian Thought Sampler [54.10960908347221]
  We model latent thought exploration as conditional sampling from learnable densities and instantiate this idea as a Gaussian Thought Sampler (GTS)<n>GTS predicts context-dependent perturbation distributions over continuous reasoning states and is trained with GRPO-style policy optimization while keeping the backbone frozen.
  arXiv  Detail & Related papers  (2026-02-15T09:57:47Z)
• Towards Sample-Efficient and Stable Reinforcement Learning for LLM-based Recommendation [56.92367609590823]
  Long Chain-of-Thought (Long CoT) reasoning has shown promise in Large Language Models (LLMs)<n>We argue that Long CoT is inherently ill-suited for the sequential recommendation domain.<n>We propose RISER, a novel Reinforced Item Space Exploration framework for Recommendation.
  arXiv  Detail & Related papers  (2026-01-31T10:02:43Z)
• Convergence and Generalization of Anti-Regularization for Parametric Models [0.0]
  Anti-regularization introduces a reward term with a reversed sign into the loss function.<n>We formalize spectral safety conditions and trust-region constraints.<n>We design a lightweight safeguard that combines a projection operator with gradient clipping to guarantee stable intervention.
  arXiv  Detail & Related papers  (2025-08-24T15:34:17Z)
• Robust Stochastic Optimization via Gradient Quantile Clipping [6.2844649973308835]
  We introduce a quant clipping strategy for Gradient Descent (SGD) We use gradient new outliers as norm clipping chains. We propose an implementation of the algorithm using Huberiles.
  arXiv  Detail & Related papers  (2023-09-29T15:24:48Z)
• Differentiable Annealed Importance Sampling and the Perils of Gradient Noise [68.44523807580438]
  Annealed importance sampling (AIS) and related algorithms are highly effective tools for marginal likelihood estimation. Differentiability is a desirable property as it would admit the possibility of optimizing marginal likelihood as an objective. We propose a differentiable algorithm by abandoning Metropolis-Hastings steps, which further unlocks mini-batch computation.
  arXiv  Detail & Related papers  (2021-07-21T17:10:14Z)
• On The Verification of Neural ODEs with Stochastic Guarantees [14.490826225393096]
  We show that Neural ODEs, an emerging class of timecontinuous neural networks, can be verified by solving a set of global-optimization problems. We introduce Lagran Reachability ( SLR), an abstraction-based technique for constructing a tight Reachtube.
  arXiv  Detail & Related papers  (2020-12-16T11:04:34Z)

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.