作者位次 #3/9ACL 2026Poster· Natural Language Processing
CODERL +: Improving Code Generation via Reinforcement with Execution Semantics Alignment
Xue Jiang · Yihong Dong · Mengyang Liu · Deng Hongyi · Tian Wang · Yongding Tao · Zhi Jin · Wenpin Jiao · Ge Li
摘要
While Large Language Models (LLMs) excel at code generation by learning from vast code corpora, a fundamental semantic gap remains between their training on textual patterns and the goal of functional correctness, which is governed by formal execution semantics. Reinforcement Learning with Verifi...