Saved in:
Bibliographic Details
Main Authors: Lei, Bin, Li, Yuchen, Chen, Qiuwu
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.14906
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929357035929600
author Lei, Bin
Li, Yuchen
Chen, Qiuwu
author_facet Lei, Bin
Li, Yuchen
Chen, Qiuwu
contents 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}.
format Preprint
id arxiv_https___arxiv_org_abs_2405_14906
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AutoCoder: Enhancing Code Large Language Model with \textsc{AIEV-Instruct}
Lei, Bin
Li, Yuchen
Chen, Qiuwu
Software Engineering
Artificial Intelligence
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}.
title AutoCoder: Enhancing Code Large Language Model with \textsc{AIEV-Instruct}
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2405.14906