SHAPE: Stage-aware Hierarchical Advantage via Potential Estimation for LLM Reasoning.
Zhengyang Ai, Zikang Shan, Xiaodong Ai, Jingxian Tang, Hangkai Hu, Pinyan Lu
Browse the full ACL paper archive.
Zhengyang Ai, Zikang Shan, Xiaodong Ai, Jingxian Tang, Hangkai Hu, Pinyan Lu
Browse the full ACL paper archive.