SweRank: Software Issue Localization with Code Ranking
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913052384821248 |
|---|---|
| author | Reddy, Revanth Gangi Suresh, Tarun Doo, JaeHyeok Liu, Ye Nguyen, Xuan Phi Zhou, Yingbo Yavuz, Semih Xiong, Caiming Ji, Heng Joty, Shafiq |
| author_facet | Reddy, Revanth Gangi Suresh, Tarun Doo, JaeHyeok Liu, Ye Nguyen, Xuan Phi Zhou, Yingbo Yavuz, Semih Xiong, Caiming Ji, Heng Joty, Shafiq |
| contents | Software issue localization, the task of identifying the precise code locations (files, classes, or functions) relevant to a natural language issue description (e.g., bug report, feature request), is a critical yet time-consuming aspect of software development. While recent LLM-based agentic approaches demonstrate promise, they often incur significant latency and cost due to complex multi-step reasoning and relying on closed-source LLMs. Alternatively, traditional code ranking models, typically optimized for query-to-code or code-to-code retrieval, struggle with the verbose and failure-descriptive nature of issue localization queries. To bridge this gap, we introduce SweRank, an efficient and effective retrieve-and-rerank framework for software issue localization. To facilitate training, we construct SweLoc, a large-scale dataset curated from public GitHub repositories, featuring real-world issue descriptions paired with corresponding code modifications. Empirical results on SWE-Bench-Lite and LocBench show that SweRank achieves state-of-the-art performance, outperforming both prior ranking models and costly agent-based systems using closed-source LLMs like Claude-3.5. Further, we demonstrate SweLoc's utility in enhancing various existing retriever and reranker models for issue localization, establishing the dataset as a valuable resource for the community. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_07849 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SweRank: Software Issue Localization with Code Ranking Reddy, Revanth Gangi Suresh, Tarun Doo, JaeHyeok Liu, Ye Nguyen, Xuan Phi Zhou, Yingbo Yavuz, Semih Xiong, Caiming Ji, Heng Joty, Shafiq Software Engineering Artificial Intelligence Information Retrieval Software issue localization, the task of identifying the precise code locations (files, classes, or functions) relevant to a natural language issue description (e.g., bug report, feature request), is a critical yet time-consuming aspect of software development. While recent LLM-based agentic approaches demonstrate promise, they often incur significant latency and cost due to complex multi-step reasoning and relying on closed-source LLMs. Alternatively, traditional code ranking models, typically optimized for query-to-code or code-to-code retrieval, struggle with the verbose and failure-descriptive nature of issue localization queries. To bridge this gap, we introduce SweRank, an efficient and effective retrieve-and-rerank framework for software issue localization. To facilitate training, we construct SweLoc, a large-scale dataset curated from public GitHub repositories, featuring real-world issue descriptions paired with corresponding code modifications. Empirical results on SWE-Bench-Lite and LocBench show that SweRank achieves state-of-the-art performance, outperforming both prior ranking models and costly agent-based systems using closed-source LLMs like Claude-3.5. Further, we demonstrate SweLoc's utility in enhancing various existing retriever and reranker models for issue localization, establishing the dataset as a valuable resource for the community. |
| title | SweRank: Software Issue Localization with Code Ranking |
| topic | Software Engineering Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2505.07849 |