Resolving Java Code Repository Issues with iSWE Agent
This addresses the need for better automated issue resolution in enterprise software development, where Java is widely used, but it is incremental as it builds on existing agent-based methods with a focus on a specific language.
The paper tackled the problem of automated issue resolution for Java code repositories, which is under-explored compared to Python, and introduced iSWE Agent, achieving state-of-the-art issue resolution rates on Java splits of Multi-SWE-bench and SWE-PolyBench.
Resolving issues on code repositories is an important part of software engineering. Various recent systems automatically resolve issues using large language models and agents, often with impressive performance. Unfortunately, most of these models and agents focus primarily on Python, and their performance on other programming languages is lower. In particular, a lot of enterprise software is written in Java, yet automated issue resolution for Java is under-explored. This paper introduces iSWE Agent, an automated issue resolver with an emphasis on Java. It consists of two sub-agents, one for localization and the other for editing. Both have access to novel tools based on rule-based Java static analysis and transformation. Using this approach, iSWE achieves state-of-the-art issue resolution rates across the Java splits of both Multi-SWE-bench and SWE-PolyBench. More generally, we hope that by combining the best of rule-based and model-based techniques, this paper contributes towards improving enterprise software development.