T2SPO: Trajectory-to-Step Policy Optimization for Agentic RL

1. 12:00
   arXiv · Machine Learning Theory

   T2SPO：面向智能体强化学习的轨迹到步骤策略优化

   T2SPO 利用成功交互轨迹提供步骤级反馈，通过 TabPFN 回归器估计剩余距离并生成辅助信用信号，在 ALFWorld 和 WebShop 上用 1.5B 与 7B 语言模型实验，相比 GRPO 一致提升任务成功率。

Current heat 9·Comparable peak 10（Oct 2）·Comparable change over 24 hours –

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.