LAPO: Leave-One-Turn Attribution for Self-Generated Process Rewards in Multi-Turn Search Reasoning 文章

ArXiv CS.AI2026-07-16PAPERen作者: Qiang Zhu, Jiajun Wu
查看原文 →
关系图谱

LAPO: Leave-One-Turn Attribution for Self-Generated Process Rewards in Multi-Turn Search Reasoning · 相关技术

相关技术

Anomaly Preference Optimization