Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO

Hugging Face Daily Papers Papers

Summary

This paper identifies and addresses aggregation bias in GRPO-style reinforcement learning for LLMs, proposing Balanced Aggregation (BA) which improves training stability and final performance by computing token-level means separately for positive and negative subsets.

Reinforcement learning with verifiable rewards (RLVR) has become a central paradigm for improving reasoning and code generation in large language models, and GRPO-style training is widely adopted for its simplicity and effectiveness. However, an important design choice remains underexplored: how token-level policy gradient terms are aggregated within each sampled group. Standard GRPO uses sequence aggregation, while recent work has advocated token aggregation as a better alternative. We show that these two rules induce different optimization biases: token aggregation introduces sign-length coupling, while sequence aggregation implicitly downweights longer responses through sequence-level equal weighting. To address this tension, we propose Balanced Aggregation (BA), a simple drop-in replacement that computes token-level means separately within the positive and negative subsets and then combines them with sequence-count-based weights. Experiments with Qwen2.5-Math-7B and Qwen3-1.7B on DAPO-17k and Polaris, evaluated on six reasoning and coding benchmarks, show that BA consistently improves training stability and final performance over standard token and sequence aggregation. Our analysis further shows that the relative effectiveness of token and sequence aggregation is largely governed by response-length variation and the positive-negative length gap, highlighting aggregation as a critical design dimension in GRPO-style RLVR.
Original Article
View Cached Full Text

Cached at: 05/08/26, 06:53 AM

Paper page - Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO

Source: https://huggingface.co/papers/2605.04077 Authors:

,

,

,

,

,

,

,

,

,

Abstract

Balanced Aggregation improves reinforcement learning with verifiable rewards by addressing optimization biases in token-level policy gradient aggregation, leading to better training stability and performance.

Reinforcement learning with verifiable rewards(RLVR) has become a central paradigm for improving reasoning and code generation in large language models, andGRPO-style trainingis widely adopted for its simplicity and effectiveness. However, an important design choice remains underexplored: howtoken-level policy gradientterms are aggregated within each sampled group. Standard GRPO usessequence aggregation, while recent work has advocatedtoken aggregationas a better alternative. We show that these two rules induce differentoptimization biases:token aggregationintroduces sign-length coupling, whilesequence aggregationimplicitly downweights longer responses through sequence-level equal weighting. To address this tension, we proposeBalanced Aggregation(BA), a simple drop-in replacement that computes token-level means separately within the positive and negative subsets and then combines them with sequence-count-based weights. Experiments with Qwen2.5-Math-7B and Qwen3-1.7B on DAPO-17k and Polaris, evaluated on six reasoning and coding benchmarks, show that BA consistently improvestraining stabilityandfinal performanceover standard token andsequence aggregation. Our analysis further shows that the relative effectiveness of token andsequence aggregationis largely governed by response-length variation and the positive-negative length gap, highlighting aggregation as a critical design dimension in GRPO-style RLVR.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2605\.04077

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.04077 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.04077 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.04077 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles