Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning

• URL: http://arxiv.org/abs/2509.25300v1
• Date: Mon, 29 Sep 2025 17:10:35 GMT
• Title: Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning
• Authors: Zelin Tan, Hejia Geng, Mulei Zhang, Xiaohang Yu, Guancheng Wan, Yifan Zhou, Qiang He, Xiangyuan Xue, Heng Zhou, Yutao Fan, Zhongzhi Li, Zaibin Zhang, Guibin Zhang, Chen Zhang, Zhenfei Yin, Lei Bai,
• Abstract summary: We study how model scale, data volume, and computational budget interact to shape performance.<n>We find that larger models trained for fewer steps consistently outperform smaller models trained for more steps.<n>In data-constrained regimes, repeated reuse of high-quality data proves highly effective.
• Score: 42.80470927369973
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While scaling laws for large language models (LLMs) during pre-training have been extensively studied, their behavior under reinforcement learning (RL) post-training remains largely unexplored. This paper presents a systematic empirical investigation of scaling behaviors in RL-based post-training, with a particular focus on mathematical reasoning. Based on 54 experiments across diverse model sizes and training settings, we characterize how model scale, data volume, and computational budget interact to shape performance. Our analysis leads to four key findings: (1). Under a fixed computational budget, larger models trained for fewer steps consistently outperform smaller models trained for more steps. (2). Given a fixed amount of training data, larger models achieve superior sample efficiency, yielding lower loss. (3). In data-constrained regimes, repeated reuse of high-quality data proves highly effective, as final performance is primarily governed by the total number of optimization steps rather than the uniqueness of samples. (4). These scaling behaviors are robust across both base and instruction-tuned models, which share similar learning dynamics (e.g., larger models show faster convergence) even while differing in absolute accuracy. Collectively, these results provide a principled foundation and practical guidelines for efficiently scaling the reasoning capabilities of LLMs through RL post-training.

Related papers

• The Art of Scaling Reinforcement Learning Compute for LLMs [52.71086085139566]
  Reinforcement learning (RL) has become central to training large language models.<n>Despite rapidly rising compute budgets, there is no principled understanding of how to evaluate algorithmic improvements for scaling RL compute.<n>We present the first large-scale systematic study, amounting to more than 400,000 GPU-hours.
  arXiv  Detail & Related papers  (2025-10-15T17:43:03Z)
• SPaRFT: Self-Paced Reinforcement Fine-Tuning for Large Language Models [51.74498855100541]
  Large language models (LLMs) have shown strong reasoning capabilities when fine-tuned with reinforcement learning (RL)<n>We propose textbfSPaRFT, a self-paced learning framework that enables efficient learning based on the capability of the model being trained.
  arXiv  Detail & Related papers  (2025-08-07T03:50:48Z)
• Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies [66.83950068218033]
  Scaling Laws demonstrate that scaling model parameters and training data enhances learning performance.<n>Despite its potential to improve performance, the integration of scaling laws into deep reinforcement learning has not been fully realized.<n>This review addresses this gap by systematically analyzing scaling strategies in three dimensions: data, network, and training budget.
  arXiv  Detail & Related papers  (2025-08-05T08:03:12Z)
• Behavior Injection: Preparing Language Models for Reinforcement Learning [24.46625106928253]
  Reinforcement fine-tuning (RFT) has emerged as a powerful post-training technique to incentivize the reasoning ability of large language models (LLMs)<n>LLMs can respond very inconsistently to RFT: some show substantial performance gains, while others plateau or even degrade.<n>We propose behavior injection, a task-agnostic data-augmentation scheme applied prior to RL.
  arXiv  Detail & Related papers  (2025-05-25T00:54:50Z)
• Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining [74.83412846804977]
  Reinforcement learning (RL)-based fine-tuning has become a crucial step in post-training language models.<n>We present a systematic end-to-end study of RL fine-tuning for mathematical reasoning by training models entirely from scratch.
  arXiv  Detail & Related papers  (2025-04-10T17:15:53Z)
• Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining [55.262510814326035]
  Existing reweighting strategies primarily focus on group-level data importance.<n>We introduce novel algorithms for dynamic, instance-level data reweighting.<n>Our framework allows us to devise reweighting strategies deprioritizing redundant or uninformative data.
  arXiv  Detail & Related papers  (2025-02-10T17:57:15Z)
• Simplified Temporal Consistency Reinforcement Learning [19.814047499837084]
  We show that a simple representation learning approach relying on a latent dynamics model trained by latent temporal consistency is sufficient for high-performance RL. Our approach outperforms model-free methods by a large margin and matches model-based methods' sample efficiency while training 2.4 times faster.
  arXiv  Detail & Related papers  (2023-06-15T19:37:43Z)

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.