ExecVerify: White-Box RL with Verifiable Stepwise Rewards for Code Execution Reasoning

Understand

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 traces.
• However, intermediate execution steps cannot be explicitly verified during SFT, so the training objective can reduce to merely matching teacher explanations.
• Moreover, training data is typically collected without explicit control over task difficulty.