AI Coders Are Among Us: Rethinking Programming Language Grammar Towards Efficient Code Generation

TL;DR

This paper introduces AI-oriented grammar, exemplified by SimPy, a revised Python grammar designed to reduce token usage and improve computational efficiency for AI models without sacrificing code semantics or performance.

Contribution

The paper presents the first AI-oriented grammar for Python, SimPy, which minimizes tokens and enhances inference efficiency for large language models in code generation tasks.

Findings

SimPy reduces token usage by 13.5% with CodeLlama and 10.4% with GPT-4.

Programs in SimPy maintain identical AST structures to Python.

Models can perform as well or better using SimPy compared to standard Python.

Abstract

Artificial Intelligence (AI) models have emerged as another important audience for programming languages alongside humans and machines, as we enter the era of large language models (LLMs). LLMs can now perform well in coding competitions and even write programs like developers to solve various tasks, including mathematical problems. However, the grammar and layout of current programs are designed to cater the needs of human developers -- with many grammar tokens and formatting tokens being used to make the code easier for humans to read. While this is helpful, such a design adds unnecessary computational work for LLMs, as each token they either use or produce consumes computational resources. To improve inference efficiency and reduce computational costs, we propose the concept of AI-oriented grammar. This aims to represent code in a way that better suits the working mechanism of AI models. Code written with AI-oriented grammar discards formats and uses a minimum number of tokens to convey code semantics effectively. To demonstrate the feasibility of this concept, we explore and implement the first AI-oriented grammar for Python, named SimPy. SimPy is crafted by revising the original Python grammar through a series of heuristic rules. Programs written in SimPy maintain identical AST structures to those in standard Python. This allows for not only execution via a modified AST parser, but also seamless transformation between programs written in Python and SimPy, enabling human developers and LLMs to use Python and SimPy, respectively, when they need to collaborate. In the experiments, compared with Python, SimPy enables a reduction in token usage by 13.5% and 10.4% for CodeLlama and GPT-4, respectively, when completing the same set of code-related tasks. Additionally, these models can maintain or even improve their performance when using SimPy instead of Python for these tasks.