SURGE: On the Potential of Large Language Models as General-Purpose Surrogate Code Executors

TL;DR

This paper introduces SURGE, a comprehensive benchmark to evaluate large language models as surrogate code executors across diverse programming and computational tasks, revealing their potential and limitations.

Contribution

It systematically assesses LLMs' ability to predict code execution outcomes, providing new insights into their effectiveness as surrogate models for various complex programming tasks.

Findings

LLMs show promising capabilities in code prediction tasks.

Scaling laws influence LLM performance in code execution.

Data efficiency varies across different programming challenges.

Abstract

Neural surrogate models are powerful and efficient tools in data mining. Meanwhile, large language models (LLMs) have demonstrated remarkable capabilities in code-related tasks, such as generation and understanding. However, an equally important yet underexplored question is whether LLMs can serve as surrogate models for code execution prediction. To systematically investigate it, we introduce SURGE, a comprehensive benchmark with $1160$ problems covering $8$ key aspects: multi-language programming tasks, competition-level programming problems, repository-level code analysis, high-cost scientific computing, time-complexity-intensive algorithms, buggy code analysis, programs dependent on specific compilers or execution environments, and formal mathematical proof verification. Through extensive analysis of $21$ open-source and proprietary LLMs, we examine scaling laws, data efficiency, and predictive accuracy. Our findings reveal important insights about the feasibility of LLMs as efficient surrogates for computational processes. The benchmark and evaluation framework are available at https://github.com/Imbernoulli/SURGE.