Li$^{2}$SAO is a lightweight variant of Single-rollout Asynchronous Optimization (SAO) that eliminates the need for a pretrained value model by using group-relative actor‑critic bootstrapping. The method first trains the actor with a group-relative advantage and the critic with a group-centered return before switching to single‑rollout Generalized Advantage Estimation. Experiments on single‑turn reasoning and multi‑turn agentic tasks show that Li$^{2}$SAO matches or surpasses the performance of GRPO, especially in early training stages.
By Zichen Bai, Yanli Wang, Yang Liu, Junhao Shi, Xueqin Liu, Jinguo Sun, Muye Li, Shaoqiang Zheng, Xuefei Diao, Zhuwei Zeng, Nan Duan, Peng Cao
Reinforcement 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.
arXiv:2607. 07508v1 Announce Type: cross Abstract: Reinforcement learning (RL) is becoming increasingly important for post-training large language models (LLMs).
By Zhenyu Hou, Yujiang Li, Jie Tang, Yuxiao Dong
arXiv:2608. 19842v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) has become a critical stage in the post-training of large language models.
By Dayang Liang, Lang Feng, Bo An, Yunlong Liu
Agentic reinforcement learning (RL) has become a critical stage in the post-training of large language models. Existing critic-free, group-relative methods estimate policy advantages from multiple rollouts, avoiding the substantial memory overhead of conventional proximal policy optimization (PPO) and achieving strong performance on long-horizon interactive tasks.
ThunderSyncRL is a training framework that eliminates idle time in agentic reinforcement learning by starting gradient computation immediately once all necessary inputs are available, thereby avoiding policy staleness. It applies to group relative policy optimization (GRPO) by computing trajectory score gradients as soon as rewards arrive, and to on‑policy distillation (OPD) by updating gradients for completed agentic turns while tool calls execute. Experiments on SWE‑bench Verified and Terminal Bench 4.0 show that ThunderSyncRL matches synchronous training performance up to 1.9× faster and outperforms asynchronous training by up to 2.47 percentage points at a fixed budget.