LoongSage：面向前沿 LLM 的生产级高效 Agentic RL 框架
LoongSage: A Production-Grade, High-Efficiency Agentic RL Framework for Frontier LLMs with Validated Recipes
LoongSage 团队发布面向前沿 LLM 的 Agentic RL 框架 LoongSage，核心代码约 14K 行，基于 Megatron 做分布式训练、SGLang 做高吞吐推理。
Computer Science > Machine Learning
arXiv:2610.16352 (cs)
Authors:LoongSage Team: Bowei Song, Caiwei Zhao, Chuwen Liu, Dechuang Gu, Dong Fang, Feiyu Xie, Huaiyu Li, Hui Zhang, Jian Tian, Jian Wang, Jie Zhao, Liguang Li, Maoyun Wang, Meiyan Yang, Minghan Zhu, Pai Liu, Pandeng Yao, Renbao Tian, Ru Yang, Shuai Jia, Shuai Tan, Shuailong Li, Shuliang Li, Teng Jin, Tianze Yang, Wenbo Cui, Wenjing Bai, Wenkang Wu, Xiaowei Jiang, Xiaoyi Dong, Yanpeng Wang, Yanwen Wang, Yaohui Ma, Yawen Wang, Yihang Zhang, Yingjie Yan, Zhanbiao Lian, Zhenyu Lu, Zhida Hu, Zhihui Hao, Zhihui Hu, Zhiwen Xiao, Zhiyi Gao, Zhongwei Qi, Zhuangzhuang Wu, Ziqian Liu, Ziyue Zheng
Abstract:Reinforcement learning (RL) has emerged as a critical phase in the post-training pipeline of large language models (LLMs). As the frontier of LLM capabilities shifts from static reasoning to agentic tasks--characterized by external tool invocation, multi-turn interactions, and long-horizon decision-making--existing mainstream RL frameworks have grown increasingly unwieldy, raising the overhead of adoption, usage, and debugging. To address these challenges, we present LoongSage, an agent-native, fully asynchronous RL framework with a lightweight core of roughly 14K lines of code. Built upon Megatron for distributed training and SGLang for high-throughput inference, LoongSage centralizes orchestration within a single controller process and encapsulates all GPU-resident components as Ray actors. It introduces AgentFlow, a unified execution paradigm that orchestrates both white-box and black-box agents. For asynchronous execution, it integrates sliding-window strategies that bound trajectory staleness, and employs TransferMesh, a topology-aware synchronization mechanism that routes weights after each step over the fastest transport available to each receiver. Beyond agentic RL, LoongSage incorporates a memory-efficient Teacher Manager that decouples the scaling of teacher models from GPU memory constraints, natively supporting Multi-Teacher On-Policy Distillation. Extensive evaluations across four complete training runs, spanning complex reinforcement learning and multi-teacher distillation, demonstrate that task rewards improve steadily while the train-inference gap is kept under continuous control, and the fully asynchronous pipeline removes synchronous idle bubbles, sustaining hardware utilization.
| Subjects: | Machine Learning (cs.LG); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.16352 [cs.LG] |
| (or arXiv:2610.16352v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.16352 arXiv-issued DOI via DataCite |
Submission history
From: Minghan Zhu [view email]
[v1]
Mon, 12 Oct 2026 08:08:16 UTC (998 KB)
[v2]
Fri, 16 Oct 2026 03:07:10 UTC (998 KB)
Current browse context:
cs.LG
Change to browse by:
Bookmark
Bibliographic and Citation Tools
Code, Data and Media Associated with this Article
Demos
Recommenders and Search Tools
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
来源：arXiv cs.CL · arxiv.org