
AutoRL: A Multi-Agent System towards Autonomous Reinforcement Learning
AutoRL keeps reinforcement-learning training under continuous multi-agent supervision: four perceptors detect failures or plateaus, three proposers diagnose and debate interventions, and an orchestrator applies online hot updates or checkpoint-based cold resumptions. Across Qwen3 and LongCat-Flash-Lite, it outperforms static GRPO recipes and a general coding agent.
Simon Tang, Wenjie Shi, Yongjing Yin · 53 views · Nov 13, 2026
LLMReinforcement Learning
Nov 13, 2026