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

본문 미리보기

arXiv:2607.13501v1 Announce Type: new Abstract: Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and harmful intermediate interactions. We propose LAPO, a self-generated process-supervision method based on backward leave-one-turn attribution. For each search turn, LAPO replaces the turn and its retrieval observation with a fixed [DELETE] placeholder and measures the resulting change in the current po