Tag
Qwen发布QwenGyre，一个面向超长时序（XLong）智能体训练的弹性强化学习框架，包含弹性调度器与轨迹处理器，在Qwen3.8-2.4T-A95B上将NL2RepoBench从52.5%提升至58.5%，并缩短约44%的端到端训练时间。
SGLang is announced as the native rollout engine for Miles v0.1, an open-source reinforcement learning framework for LLMs and multimodal models, aimed at improving throughput, cache efficiency, and stability in RL training at scale.
Prime-rl adds a first-class algorithms layer with six built-in RL algorithms (GRPO, MaxRL, OPD, OPSD, SFT, ECHO), making it easier to implement custom algorithms with a single file.
Z. ai has open-sourced its RL infrastructure, the slime framework, which enabled efficient OPD post-training of GLM-5.2 in about two days. slime is an LLM post-training framework for RL scaling that integrates Megatron and SGLang, and has been battle-tested by frontier models like GLM, Qwen, DeepSeek, and Llama.