Resolving Java Code Repository Issues with iSWE Agent

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ganhotra, Jatin, Serhan, Sami, Nassar, Antonio Abu, Shinnar, Avraham, Nevo, Ziv, Hirzel, Martin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917333778300928
author Ganhotra, Jatin
Serhan, Sami
Nassar, Antonio Abu
Shinnar, Avraham
Nevo, Ziv
Hirzel, Martin
author_facet Ganhotra, Jatin
Serhan, Sami
Nassar, Antonio Abu
Shinnar, Avraham
Nevo, Ziv
Hirzel, Martin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_11356
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Resolving Java Code Repository Issues with iSWE Agent
Ganhotra, Jatin
Serhan, Sami
Nassar, Antonio Abu
Shinnar, Avraham
Nevo, Ziv
Hirzel, Martin
Software Engineering
Artificial Intelligence
Multiagent Systems
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.
title Resolving Java Code Repository Issues with iSWE Agent
topic Software Engineering
Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2603.11356