Prompting Is All You Need: Automated Android Bug Replay with Large Language Models

Bug reports are vital for software maintenance that allow users to inform developers of the problems encountered while using the software. As such, researchers have committed considerable resources toward automating bug replay to expedite the process of software maintenance. Nonetheless, the success...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings / International Conference on Software Engineering pp. 803 - 815
Main Authors: Feng, Sidong, Chen, Chunyang
Format: Conference Proceeding
Language:English
Published: ACM 14.04.2024
Subjects:
automated bug replay
Cognition
Computer bugs
large language model
Manuals
Natural language processing
prompt engineering
Software maintenance
Training
Vocabulary
ISSN:1558-1225
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Bug reports are vital for software maintenance that allow users to inform developers of the problems encountered while using the software. As such, researchers have committed considerable resources toward automating bug replay to expedite the process of software maintenance. Nonetheless, the success of current au-tomated approaches is largely dictated by the characteristics and quality of bug reports, as they are constrained by the limitations of manually-crafted patterns and predefined vocabulary lists. In-spired by the success of Large Language Models (LLMs) in natural language understanding, we propose AdbGPT, a new lightweight approach to automatically reproduce the bugs from bug reports through prompt engineering, without any training and hard-coding effort. AdbGPT leverages few-shot learning and chain-of-thought reasoning to elicit human knowledge and logical reasoning from LLMs to accomplish the bug replay in a manner similar to a devel-oper. Our evaluations demonstrate the effectiveness and efficiency of our AdbGPT to reproduce 81.3% of bug reports in 253.6 seconds, outperforming the state-of-the-art baselines and ablation studies. We also conduct a small-scale user study to confirm the usefulness of AdbGPT in enhancing developers' bug replay capabilities.
ISSN:1558-1225
DOI:10.1145/3597503.3608137