# When Do Larger Batches Help Scale LLM Reinforcement Learning?

arXiv: https://arxiv.org/abs/2608.29296 · HTML: https://mlsanity.com/paper/2608.29296/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 29 references that are in the map.
- First posted on arXiv 29 Aug 2026.

## Builds on (most cited first, 24 of 24)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [Efficiently Scaling Transformer Inference](https://mlsanity.com/paper/2211.05102/) (2022)
- [Don't Decay the Learning Rate, Increase the Batch Size](https://mlsanity.com/paper/1711.00489/) (2017)
- [An Empirical Model of Large-Batch Training](https://mlsanity.com/paper/1812.06162/) (2018)
- [AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning](https://mlsanity.com/paper/2505.24298/) (2025)
- [Measuring the Effects of Data Parallelism on Neural Network Training](https://mlsanity.com/paper/1811.03600/) (2018)
- [ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models](https://mlsanity.com/paper/2310.10505/) (2023)
- [On the SDEs and Scaling Rules for Adaptive Gradient Algorithms](https://mlsanity.com/paper/2205.10287/) (2022)
- [Batch size-invariance for policy optimization](https://mlsanity.com/paper/2110.00641/) (2021)
- [PipelineRL: Faster On-policy Reinforcement Learning for Long Sequence Generation](https://mlsanity.com/paper/2509.19128/) (2025)
- [Improving Sampling Efficiency in RLVR through Adaptive Rollout and Response Reuse](https://mlsanity.com/paper/2509.25808/) (2025)
- [BroRL: Scaling Reinforcement Learning via Broadened Exploration](https://mlsanity.com/paper/2510.01180/) (2025)
- [Critical Batch Size Revisited: A Simple Empirical Approach to Large-Batch Language Model Training](https://mlsanity.com/paper/2505.23971/) (2025)
- [Adaptive Rollout Allocation for Online Reinforcement Learning with Verifiable Rewards](https://mlsanity.com/paper/2602.01601/) (2026)
- [Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning](https://mlsanity.com/paper/2306.08590/) (2023)
- [IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RL](https://mlsanity.com/paper/2603.12151/) (2026)

## Built on by (most cited first, 2 of 2)

- [EasyPPO: Stabilizing the Critic Is Key](https://mlsanity.com/paper/2609.36802/) (2026)
- [Two Clocks: Why Larger Rollout Batches Learn Slower but Fail on Schedule in Reinforcement Learning with Verifiable Rewards](https://mlsanity.com/paper/2610.18853/) (2026)

## Abstract (arXiv)

Larger batches reduce the variance of stochastic gradients per update and are therefore often expected to accelerate training. Yet whether this statistical benefit translates into lower wall-clock time-to-target remains unclear, because each update consumes more samples and may take longer to execute. We study this tradeoff in reinforcement learning for large language models. We separate its algorithmic and systems effects by comparing learning and execution along their natural axes. At the algorithmic level, we compare configurations at equal cumulative sample counts while retuning batch-dependent hyperparameters. Over a bounded range of batch sizes, this procedure yields an approximately batch-size-invariant family whose members follow similar sample-indexed learning trajectories. At the systems level, we exploit the computational asymmetry between rollout generation and training: autoregressive generation is often memory-bandwidth-bound at low concurrency, whereas training work scales approximately with the number of processed tokens. Combining these two views yields a direct decision rule: a larger-batch configuration reduces time-to-target only when its throughput gain exceeds its samples-to-target penalty. Experiments with GRPO and PPO support both sides of this decomposition. At the algorithmic level, square-root learning-rate scaling with Adam produces approximately batch-size-invariant learning curves over a bounded range of batch sizes. At the systems level, larger batches improve generation throughput by up to 2.29x on fixed hardware. In GRPO, combining higher throughput with learning-rate retuning reduces time-to-target by up to 29%, whereas increasing the batch without retuning is slower despite its higher throughput.