Lean4AgenticRL: Advancing Agentic RL with Verifiable Multi-level Process Rewards

One-line takeaway

Amazon's Lean4AgenticRL adds verifiable multi-level process rewards to agentic RL for software-engineering and terminal tasks, grounding tool-call, workflow-stage and outcome rewards in a unified Lean4 formalization instead of relying on outcome rewards alone.

Amazon 的 Lean4AgenticRL 给软件工程和终端任务的智能体强化学习加上多层过程奖励：把工具调用级、工作流阶段级和最终结果奖励统一建立在 Lean4 形式化之上，可验证，弥补只用最终结果奖励训练效率低的问题。