Large Language Models as Code Executors: An Exploratory Study

TL;DR

This study explores the novel use of Large Language Models as code executors, evaluating their accuracy across various models and introducing an iterative prompting technique to improve performance.

Contribution

It is the first comprehensive examination of LLMs as code executors and proposes an iterative prompting method to enhance their accuracy.

Findings

o1 model achieved over 90% accuracy in code execution

Iterative Instruction Prompting improved accuracy by up to 19.46%

Different models showed varying levels of effectiveness in code execution

Abstract

The capabilities of Large Language Models (LLMs) have significantly evolved, extending from natural language processing to complex tasks like code understanding and generation. We expand the scope of LLMs' capabilities to a broader context, using LLMs to execute code snippets to obtain the output. This paper pioneers the exploration of LLMs as code executors, where code snippets are directly fed to the models for execution, and outputs are returned. We are the first to comprehensively examine this feasibility across various LLMs, including OpenAI's o1, GPT-4o, GPT-3.5, DeepSeek, and Qwen-Coder. Notably, the o1 model achieved over 90% accuracy in code execution, while others demonstrated lower accuracy levels. Furthermore, we introduce an Iterative Instruction Prompting (IIP) technique that processes code snippets line by line, enhancing the accuracy of weaker models by an average of 7.22% (with the highest improvement of 18.96%) and an absolute average improvement of 3.86% against CoT prompting (with the highest improvement of 19.46%). Our study not only highlights the transformative potential of LLMs in coding but also lays the groundwork for future advancements in automated programming and the completion of complex tasks.