ReCo: Reweighting GRPO Against Distributional Concentration

• URL: http://arxiv.org/abs/2607.26862v1
• Date: Wed, 29 Jul 2026 12:45:55 GMT
• Title: ReCo: Reweighting GRPO Against Distributional Concentration
• Abstract summary: GRPO can reduce the base model's reasoning capacity and underperform it in Pass@k when k is large.<n>We find that this reduction is associated with GRPO concentrating on responses that the base model already generates with high probability.<n>We propose ReCo, a reweighting method that addresses both effects.
• Score: 8.37802307992348
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Group Relative Policy Optimization (GRPO) has become a standard reinforcement learning method for post-training language models. Recent work shows that GRPO can reduce the base model's reasoning capacity and underperform it in Pass@k when k is large, indicating reduced coverage of reasoning paths. We find that this reduction is associated with GRPO concentrating on responses that the base model already generates with high probability. We trace this concentration to two mechanisms in the GRPO update. At the response level, high-probability responses dominate the group gradient through repeated occurrence. At the token level, GRPO's importance ratio scales gradients, further reinforcing tokens that become more likely under the current policy. We propose ReCo, a reweighting method that addresses both effects. Response contributions are normalized by their expected occurrence within the rollout group, and the token-level importance ratio is replaced with a variance-based ratio that gives larger update scale to non-saturated decision points where alternative token choices remain plausible. Across Qwen2.5-Math-1.5B/7B and Llama-3.1-8B-Instruct on five mathematical reasoning benchmarks, ReCo improves Pass@k for large values of k and is comparable to GRPO for small values of k.

Related papers

• Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective [10.958642517467721]
  We present a framework for Contrastive Sequence-level Policy Optimization in RLVR.<n>ConSPO replaces GRPO's clipped ratio-based scores with length-normalized sequence log-probabilities.<n>ConSPO consistently outperforms several strong RLVR baselines on challenging mathematical reasoning benchmarks.
  arXiv  Detail & Related papers  (2026-05-13T04:02:36Z)
• Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO [70.38763678943648]
  Reinforcement learning with verifiable rewards (RLVR) has become a central paradigm for improving reasoning and code generation in large language models.<n>Standard GRPO uses sequence aggregation, while recent work has advocated token aggregation as a better alternative.<n>We show that these two rules induce different optimization biases; token aggregation introduces sign-length coupling, while sequence aggregation implicitly downweights longer responses.
  arXiv  Detail & Related papers  (2026-04-14T09:48:46Z)
• 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)
• 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)
• SSPO: Subsentence-level Policy Optimization [11.74548168856559]
  This paper introduces SSPO, which applies sentence-level importance ratio, taking the balance between GRPO and GSPO.<n>SSPO achieves an average score of 46.57 across five datasets, surpassing GRPO (43.01) and GSPO (44.42) and wins state-of-the-art performance on three datasets.
  arXiv  Detail & Related papers  (2025-11-06T10:48:31Z)
• $λ$-GRPO: Unifying the GRPO Frameworks with Learnable Token Preferences [22.199479724764725]
  We introduce a learnable parameter $lambda$ that adaptively controls token-level weighting.<n>We find that $lambda$-GRPO achieves consistent improvements over vanilla GRPO and DAPO.<n>These gains come without any modifications to the training data or additional computational cost.
  arXiv  Detail & Related papers  (2025-10-08T10:39:07Z)
• On the Theory and Practice of GRPO: A Trajectory-Corrected Approach with Fast Convergence [2.8165669455824696]
  Group Relative Policy Optimization is a critic-free reinforcement learning algorithm.<n>We show that GRPO update rule estimates the policy gradient at the old policy rather than the current one.<n>We propose a new algorithm: Trajectory level Importance Corrected GRPO.
  arXiv  Detail & Related papers  (2025-08-04T19:01:19Z)
• Geometric-Mean Policy Optimization [117.05113769757172]
  Group Relative Policy Optimization ( GRPO) has significantly enhanced the reasoning capability of large language models.<n> GRPO is observed to suffer from unstable policy updates when facing tokens with outlier importance-weighted rewards.<n>We propose Geometric-Mean Policy Optimization (GMPO) to improve the stability of GRPO through suppressing token reward outliers.
  arXiv  Detail & Related papers  (2025-07-28T09:54:05Z)
• 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: 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)

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.