SweRank+: Multilingual, Multi-Turn Code Ranking for Software Issue Localization
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_ | 1866914217579249664 |
|---|---|
| author | Reddy, Revanth Gangi Liu, Ye Zhao, Wenting Doo, JaeHyeok Suresh, Tarun Lee, Daniel Xiong, Caiming Zhou, Yingbo Yavuz, Semih Joty, Shafiq |
| author_facet | Reddy, Revanth Gangi Liu, Ye Zhao, Wenting Doo, JaeHyeok Suresh, Tarun Lee, Daniel Xiong, Caiming Zhou, Yingbo Yavuz, Semih Joty, Shafiq |
| contents | Maintaining large-scale, multilingual codebases hinges on accurately localizing issues, which requires mapping natural-language error descriptions to the relevant functions that need to be modified. However, existing ranking approaches are often Python-centric and perform a single-pass search over the codebase. This work introduces SweRank+, a framework that couples SweRankMulti, a cross-lingual code ranking tool, with SweRankAgent, an agentic search setup, for iterative, multi-turn reasoning over the code repository. SweRankMulti comprises a code embedding retriever and a listwise LLM reranker, and is trained using a carefully curated large-scale issue localization dataset spanning multiple popular programming languages. SweRankAgent adopts an agentic search loop that moves beyond single-shot localization with a memory buffer to reason and accumulate relevant localization candidates over multiple turns. Our experiments on issue localization benchmarks spanning various languages demonstrate new state-of-the-art performance with SweRankMulti, while SweRankAgent further improves localization over single-pass ranking. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_20482 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SweRank+: Multilingual, Multi-Turn Code Ranking for Software Issue Localization Reddy, Revanth Gangi Liu, Ye Zhao, Wenting Doo, JaeHyeok Suresh, Tarun Lee, Daniel Xiong, Caiming Zhou, Yingbo Yavuz, Semih Joty, Shafiq Software Engineering Artificial Intelligence Maintaining large-scale, multilingual codebases hinges on accurately localizing issues, which requires mapping natural-language error descriptions to the relevant functions that need to be modified. However, existing ranking approaches are often Python-centric and perform a single-pass search over the codebase. This work introduces SweRank+, a framework that couples SweRankMulti, a cross-lingual code ranking tool, with SweRankAgent, an agentic search setup, for iterative, multi-turn reasoning over the code repository. SweRankMulti comprises a code embedding retriever and a listwise LLM reranker, and is trained using a carefully curated large-scale issue localization dataset spanning multiple popular programming languages. SweRankAgent adopts an agentic search loop that moves beyond single-shot localization with a memory buffer to reason and accumulate relevant localization candidates over multiple turns. Our experiments on issue localization benchmarks spanning various languages demonstrate new state-of-the-art performance with SweRankMulti, while SweRankAgent further improves localization over single-pass ranking. |
| title | SweRank+: Multilingual, Multi-Turn Code Ranking for Software Issue Localization |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2512.20482 |