AgentFly: Scaling Agentic Reinforcement Learning with Unified Resource System.
arXiv:2507.14897v3 Announce Type: replace Abstract: Methods to build LLM agents have evolved from prompt engineering and supervised finetuning to agentic reinforcement learning (agentic RL). However, agentic RL remains bottlenecked by its surrounding systems:
arXiv cs.AIResearch source·