SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering 文章

ArXiv CS.CL2026-06-02NEWSen作者: Qiming Shi, Zhaolu Kang, Yunfan Zhou, Di Weng, Yingcai Wu

SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering · 相关技术