TL;DR: AgentFlow is a trainable agent framework with four modules—Planner, Executor, Verifier, Generator—coordinated by an explicit memory and toolset. The planner is optimized in the loop with a new on-policy method, Flow-GRPO, which broadcasts a trajectory-level outcome reward to every turn and applies token-level PPO-style updates with KL regularization and group-normalized advantages. On ten benchmarks, […]
The post Stanford Researchers Released AgentFlow: In-the-Flow Reinforcement Learning RL for Modular, Tool-Using AI Agents appeared first on MarkTechPost.