LGAIMay 30, 2025

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Tsinghua
arXiv:2505.24298v3176 citationsh-index: 9Has Code
Originality Highly original
AI Analysis

This addresses a system-level bottleneck for researchers and practitioners training large language models on reasoning tasks, offering a significant efficiency improvement.

The paper tackles the inefficiency of synchronous reinforcement learning systems for large language models by introducing AReaL, a fully asynchronous system that decouples generation from training, achieving up to 2.77x training speedup with matched or improved performance on math and code reasoning benchmarks.

Reinforcement learning (RL) has become a dominant paradigm for training large language models (LLMs), particularly for reasoning tasks. Effective RL for LLMs requires massive parallelization and poses an urgent need for efficient training systems. Most existing large-scale RL systems for LLMs are synchronous, alternating generation and training in a batch setting where rollouts in each training batch are generated by the same model. This approach stabilizes RL training but suffers from severe system-level inefficiency: generation must wait until the longest output in the batch is completed before model updates, resulting in GPU underutilization. We present AReaL, a fully asynchronous RL system that completely decouples generation from training. Rollout workers in AReaL continuously generate new outputs without waiting, while training workers update the model whenever a batch of data is collected. AReaL also incorporates a collection of system-level optimizations, leading to substantially higher GPU utilization. To stabilize RL training, AReaL balances the workload of rollout and training workers to control data staleness, and adopts a staleness-enhanced PPO variant to better handle outdated training samples. Extensive experiments on math and code reasoning benchmarks show that AReaL achieves up to 2.77$\times$ training speedup compared to synchronous systems with the same number of GPUs and matched or improved final performance. The code of AReaL is available at https://github.com/inclusionAI/AReaL/.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes