Setup AGent (SAG): A Dual-Model LLM Agent for Autonomous End-to-End Java Project Configuration

Proceedings of the IEEE/ACM 48th International Conference on Software Engineering 2026 Open access

Read full text
Authors: Chenhao Wei, Gengwu Zhao, Xinyi Li, Billy Ye, Lu Xiao
DOI: 10.1145/3786582.3786818
Cited by: 1
References: 10

Abstract

Environment setup remains a critical bottleneck in software development, with Java projects presenting unique challenges due to complex build tool configurations, transitive dependencies, and compilation requirements. While existing solutions like Installamatic achieve 55% success on Python repositories, Java/JVM repositories show only 29.47% success rates with current approaches.

Fields of Study & Subjects

Software System Performance and Reliability Software Engineering Research Advanced Software Engineering Methodologies

Publication details

Journal / source
Proceedings of the IEEE/ACM 48th International Conference on Software Engineering
Publisher
ACM
Pages
96–100
Publication date
12 April 2026