titleSingle-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
authorsZhenyu Hou, Yujiang Li, Jie Tang, Yuxiao Dong
date2026-07-08
venuearXiv (preprint, not peer reviewed)
idarXiv:2607.07508
affiliationZ.ai
upvotes33 (Hugging Face Daily Papers, 2026-11-01)
linksabs pdf hf
abstractReinforcement learning (RL) is becoming increasingly important for post-training large language models (LLMs). Previous RL pipelines for LLMs were mostly synchronous and batch-interleaved, which is inefficient for long-horizon agentic tasks. Recently, asynchronous RL has emerged as a more efficient alternative by updating the model as rollouts arrive. However, existing asynchronous RL systems often emphasize throughput, while leaving training stability and task effectiveness largely underexplored. For example, a key challenge is that group-wise sampling in the widely-used GRPO framework does not naturally fit asynchronous agentic training. In this paper, we present Single-rollout Asynchronous Optimization (SAO) to address the stability and off-policy challenges in asynchronous RL. To reduce off-policy effects and improve generalization, we replace group-wise sampling with single-rollout sampling, that is, using one rollout per prompt. We further improve this single-rollout strategy with practical value-model training designs. To improve optimization stability, we introduce a strict double-side token-level clipping strategy. SAO is able to train stably for one thousand steps and consistently outperform GRPO and its variants on agentic coding and reasoning benchmarks, such as SWE-Bench Verified, BeyondAIME, and IMOAnswerBench. We also demonstrate that single-rollout RL is particularly effective in a simulated online learning setting, where the model must adapt to changing evolving environments. To this end, SAO is successfully deployed in the agentic RL pipeline for training the open GLM-5.2 model (750B-A40B).

cite

@misc{hou2026single,
  title={Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning},
  author={Zhenyu Hou and Yujiang Li and Jie Tang and Yuxiao Dong},
  year={2026},
  eprint={2607.07508},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2607.07508}
}