Tackling Length Inflation Without Trade-offs: Group Relative Reward Rescaling for Reinforcement Learning

• URL: http://arxiv.org/abs/2603.10535v1
• Date: Wed, 11 Mar 2026 08:41:34 GMT
• Title: Tackling Length Inflation Without Trade-offs: Group Relative Reward Rescaling for Reinforcement Learning
• Abstract summary: Group Relative Reward Rescaling (GR$3$) is a general, continuous, and reward-dependent gating mechanism.<n> GR$3$maintains training dynamics and downstream performance comparable to standard GRPO.<n>It significantly mitigates length inflation, outperforming state-of-the-art length-regularized baselines.
• Score: 74.5532558466687
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning significantly enhances LLM capabilities but suffers from a critical issue: length inflation, where models adopt verbosity or inefficient reasoning to maximize rewards. Prior approaches struggle to address this challenge in a general and lossless manner, primarily because additive penalties introduce a compensatory effect that creates optimization shortcuts, while heuristic gating strategies lack generality beyond binary feedback. To bridge this gap, we present Group Relative Reward Rescaling (GR$^3$), which reframes length control as a multiplicative rescaling paradigm, effectively establishing a generalized, continuous, and reward-dependent gating mechanism. To further ensure lossless optimization, we incorporate group-relative regularization and advantage-aware calibration, which dynamically adapt length budgets to instance difficulty and preserve the advantage signal of high-quality trajectories. Empirically, across both RLHF and RLVR settings, GR$^3$~maintains training dynamics and downstream performance comparable to standard GRPO while significantly mitigating length inflation, outperforming state-of-the-art length-regularized baselines.

Related papers

• Generative Optimization for Incentivized Advertising with Global Level Constraints [22.46351828626369]
  GOAL is a constraint-aware generative framework that formulates incentive allocation as a conditional sequence generation problem.<n>We show that GOAL improves long-term revenue and user retention while substantially reducing ROI violation rates compared to strong baselines.
  arXiv  Detail & Related papers  (2026-08-05T04:04:07Z)
• Beyond Penalizing Mistakes: Stabilizing Efficiency Training in Large Reasoning Models via Adaptive Correct-Only Rewards [33.82648880607807]
  Group Relative Policy Optimization (GRPO) aims to reduce verbosity.<n> GRPO's group normalization creates divergent advantages when incorrect answers receive continuous length penalties.<n>To robustly prevent both failure modes, we propose ACOER.
  arXiv  Detail & Related papers  (2026-06-21T23:27:12Z)
• 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)
• Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping [66.25536973294726]
  Post-training methods for text-to-image (T2I) models are prone to reward hacking.<n>Super-Linear Advantage Shaping (SLAS) reshapes the local policy space.<n>SLAS consistently surpasses the DanceGRPO baseline across multiple backbones and benchmarks.
  arXiv  Detail & Related papers  (2026-05-11T17:59:25Z)
• 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)
• Unifying Stable Optimization and Reference Regularization in RLHF [64.16830602324345]
  This paper introduces a unified regularization approach that balances objectives of preventing reward hacking and maintaining stable policy updates.<n>Our simple yet principled alignment objective yields a weighted supervised fine-tuning loss with a superior trade-off, which demonstrably improves both alignment results and implementation complexity.
  arXiv  Detail & Related papers  (2026-02-12T03:31:19Z)
• Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoning [60.00161035836637]
  Group Relative Policy Optimization has emerged as a promising critic-free reinforcement learning paradigm for reasoning tasks.<n>We introduce Outcome-grounded Advantage Reshaping (OAR), a fine-grained credit assignment mechanism that redistributes advantages based on how much each token influences the model's final answer.<n>OAR-G achieves comparable gains with negligible computational overhead, both significantly outperforming a strong GRPO baseline.
  arXiv  Detail & Related papers  (2026-01-12T10:48:02Z)
• MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization [56.074760766965085]
  Group-Relative Policy Optimization has emerged as an efficient paradigm for aligning Large Language Models (LLMs)<n>We propose MAESTRO, which treats reward scalarization as a dynamic latent policy, leveraging the model's terminal hidden states as a semantic bottleneck.<n>We formulate this as a contextual bandit problem within a bi-level optimization framework, where a lightweight Conductor network co-evolves with the policy by utilizing group-relative advantages as a meta-reward signal.
  arXiv  Detail & Related papers  (2026-01-12T05:02:48Z)
• ETR: Outcome-Guided Elastic Trust Regions for Policy Optimization [6.716883192613149]
  We propose textbfElastic textbfTrust textbfETR, a dynamic mechanism that aligns optimization constraints with signal quality.<n>ETR consistently outperforms GRPO, achieving superior accuracy while effectively mitigating policy entropy degradation.
  arXiv  Detail & Related papers  (2026-01-07T09:19:53Z)
• Enhancing Agentic RL with Progressive Reward Shaping and Value-based Sampling Policy Optimization [13.475938754147625]
  Large Language Models (LLMs) empowered with Tool-Integrated Reasoning (TIR) can iteratively plan, call external tools, and integrate returned information to solve complex, long-horizon reasoning tasks.<n>Agentic Reinforcement Learning (Agentic RL) optimize such models over full tool-interaction trajectories.<n>Two key challenges hinder effectiveness: (1) Sparse, non-instructive rewards, such as binary 0-1 verifiable signals, provide limited guidance for intermediate steps and slow convergence.<n>We propose two complementary techniques: Progressive Reward Shaping (PRS) and Value-based Sampling Policy Optimization (VSPO).
  arXiv  Detail & Related papers  (2025-12-08T11:59:25Z)
• FedLoDrop: Federated LoRA with Dropout for Generalized LLM Fine-tuning [65.26899091946417]
  Fine-tuning large language models (LLMs) is crucial for adapting general-purpose models to specific tasks.<n>This paper proposes Federated LoRA with Dropout (FedLoDrop), a new framework that applies dropout to the rows and columns of the trainable matrix in Federated LoRA.
  arXiv  Detail & Related papers  (2025-10-14T02:40:45Z)

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.