Safety
A Production-Grade, High-Efficiency Agentic RL Framework for Frontier LLMs with Validated Recipes
arXiv:2610.16352v1 Announce Type: new 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 capabi
arXiv:2610.16352v1 Announce Type: new 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.
Related
- EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts
- Frontier Learning: Training LLM Reasoners at the Edge of Capability
- Bridging SFT and RL: Dynamic Policy Optimization for Robust Reasoning
- RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning
- HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models
Source: arXiv cs.LG | 2026-10-14