作者位次 #7/7ACL 2026Poster· Natural Language Processing
E xec V erify: White-Box RL with Verifiable Stepwise Rewards for Code Execution Reasoning
Lingxiao Tang · He Ye · Zhaoyang Chu · Muyang Ye · Zhongxin Liu · Xiaoxue Ren · Lingfeng Bao
摘要
Code LLMs still struggle with code execution reasoning, especially in smaller models. Existing methods rely on supervised fine-tuning (SFT) with teacher-generated explanations, primarily in two forms: (1) input–output (I/O) prediction chains and (2) natural-language descriptions of execution trac...