Execution Guided Line-by-Line Code Generation

TL;DR

This paper introduces Execution-Guided Classifier-Free Guidance (EG-CFG), a novel method that integrates real-time execution feedback into neural code generation, significantly improving the quality and correctness of generated code.

Contribution

The paper presents a new approach that incorporates execution signals during code generation, enabling more accurate and executable code outputs compared to traditional methods.

Findings

EG-CFG achieves state-of-the-art results across various coding tasks.

The method improves code correctness by using execution feedback during generation.

Parallel exploration of multiple solutions enhances diversity and performance.

Abstract

We present a novel approach to neural code generation that incorporates real-time execution signals into the language model generation process. While large language models (LLMs) have demonstrated impressive code generation capabilities, they typically do not utilize execution feedback during inference, a critical signal that human programmers regularly leverage. Our method, Execution-Guided Classifier-Free Guidance (EG-CFG), dynamically incorporates execution signals as the model generates code, providing line-by-line feedback that guides the generation process toward executable solutions. EG-CFG employs a multi-stage process: first, we conduct beam search to sample candidate program completions for each line; second, we extract execution signals by executing these candidates against test cases; and finally, we incorporate these signals into the prompt during generation. By maintaining consistent signals across tokens within the same line and refreshing signals at line boundaries, our approach provides coherent guidance while preserving syntactic structure. Moreover, the method naturally supports native parallelism at the task level in which multiple agents operate in parallel, exploring diverse reasoning paths and collectively generating a broad set of candidate solutions. Our experiments across diverse coding tasks demonstrate that EG-CFG significantly improves code generation performance compared to standard approaches, achieving state-of-the-art results across various levels of complexity, from foundational problems to challenging competitive programming and data science tasks. Our code is available at: https://github.com/boazlavon/eg_cfg