AgentFlow: when the agent's workflow learns

Introduces AgentFlow, a novel framework that makes an agent's workflow trainable. It splits agents into four modules (planner, executor, verifier, generator) and uses Flow-GRPO (flow-based group refined policy optimization) to train the planner on-policy within the live multi-turn loop. Flow-GRPO addresses credit assignment by broadcasting end-of-task outcomes back to each turn, enabling tractable single-turn updates. AgentFlow, using a 7B model, demonstrates significant performance gains across benchmarks compared to larger proprietary systems, highlighting the importance of workflow learning over model scaling alone. The post also contrasts the effectiveness of in-the-flow training (Flow-GRPO) with conventional offline supervised fine-tuning.