AutoCoder: Enhancing Code Large Language Model with \textsc{AIEV-Instruct}
This work addresses the need for more accurate and flexible code generation tools for developers, representing a strong incremental advance in the field.
The paper tackles the problem of improving code generation by large language models, achieving a pass@1 score of 90.9% on the Human Eval benchmark, surpassing GPT-4 Turbo and GPT-4o, and introduces a more versatile code interpreter.
We introduce AutoCoder, the first Large Language Model to surpass GPT-4 Turbo (April 2024) and GPT-4o in pass@1 on the Human Eval benchmark test ($\mathbf{90.9\%}$ vs. $\mathbf{90.2\%}$). In addition, AutoCoder offers a more versatile code interpreter compared to GPT-4 Turbo and GPT-4o. It's code interpreter can install external packages instead of limiting to built-in packages. AutoCoder's training data is a multi-turn dialogue dataset created by a system combining agent interaction and external code execution verification, a method we term \textbf{\textsc{AIEV-Instruct}} (Instruction Tuning with Agent-Interaction and Execution-Verified). Compared to previous large-scale code dataset generation methods, \textsc{AIEV-Instruct} reduces dependence on proprietary large models and provides execution-validated code dataset. The code and the demo video is available in \url{https://github.com/bin123apple/AutoCoder}.