{"ID":2825895,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.20482","arxiv_id":"2512.20482","title":"SweRank+: Multilingual, Multi-Turn Code Ranking for Software Issue Localization","abstract":"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.","short_abstract":"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 wo...","url_abs":"https://arxiv.org/abs/2512.20482","url_pdf":"https://arxiv.org/pdf/2512.20482v1","authors":"[\"Revanth Gangi Reddy\",\"Ye Liu\",\"Wenting Zhao\",\"JaeHyeok Doo\",\"Tarun Suresh\",\"Daniel Lee\",\"Caiming Xiong\",\"Yingbo Zhou\",\"Semih Yavuz\",\"Shafiq Joty\"]","published":"2025-12-23T16:18:39Z","proceeding":"cs.SE","tasks":"[\"cs.SE\",\"cs.AI\"]","methods":"[\"Large Language Model\"]","has_code":false}