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.
@article{arxiv.2512.20482,
title = {SweRank+: Multilingual, Multi-Turn Code Ranking for Software Issue Localization},
author = {Revanth Gangi Reddy and Ye Liu and Wenting Zhao and JaeHyeok Doo and Tarun Suresh and Daniel Lee and Caiming Xiong and Yingbo Zhou and Semih Yavuz and Shafiq Joty},
journal= {arXiv preprint arXiv:2512.20482},
year = {2025}
}