DRA-GRPO: Your GRPO Needs to Know Diverse Reasoning Paths for Mathematical Reasoning.

Xiwen Chen, Wenhui Zhu, Peijie Qiu, Xuanzhao Dong, Hao Wang, Haiyu Wu, Huayu Li, Aris Sotiras, Yalin Wang, Abolfazl Razi

Browse the full ACL paper archive.