paper-with-me

홈 › Papers

Resolving Java Code Repository Issues with iSWE Agent

2026-03-11 · Jatin Ganhotra, Sami Serhan, Antonio Abu Nassar, Avraham Shinnar, Ziv Nevo, Martin Hirzel arxiv

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.

📄 PDF Abstract BibTeX arXiv:2603.11356

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

CodeR: Issue Resolving with Multi-Agent and Task Graphs

2024-06-03 · Dong Chen, Shaoxin Lin, Muhan Zeng, Daoguang Zan 외

GitHub issue resolving recently has attracted significant attention from academia and industry. SWE-bench is proposed to measure the performance in resolving issues. In this paper, we propose CodeR, which adopts a multi-…

Bug fixing

Repository Structure-Aware Training Makes SLMs Better Issue Resolver

2024-12-26 · Zexiong Ma, Shengnan An, Zeqi Lin, Yanzhen Zou 외

Language models have been applied to various software development tasks, but the performance varies according to the scale of the models. Large Language Models (LLMs) outperform Small Language Models (SLMs) in complex ta…

Long-Context Understanding

CodeV: Issue Resolving with Visual Data

2024-12-23 · Linhao Zhang, Daoguang Zan, Quanshun Yang, Zhirong Huang 외

Large Language Models (LLMs) have advanced rapidly in recent years, with their applications in software engineering expanding to more complex repository-level tasks. GitHub issue resolving is a key challenge among these …

MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution

2024-03-26 · Wei Tao, Yucheng Zhou, Yanlin Wang, Wenqiang Zhang 외

In software development, resolving the emergent issues within GitHub repositories is a complex challenge that involves not only the incorporation of new code but also the maintenance of existing code. Large Language Mode…

Code GenerationGitHub issue resolution

ReCodeAgent: A Multi-Agent Workflow for Language-agnostic Translation and Validation of Large-scale Repositories

2026-04-08 · Ali Reza Ibrahimzada, Brandon Paulsen, Daniel Kroening, Reyhaneh Jabbarvand arxiv

Most repository-level code translation and validation techniques have been evaluated on a single source-target programming language (PL) pair, owing to the complex engineering effort required to adapt new PL pairs. Progr…

Code Translation