SweRank+: Multilingual, Multi-Turn Code Ranking for Software Issue Localization
- URL: http://arxiv.org/abs/2512.20482v1
- Date: Tue, 23 Dec 2025 16:18:39 GMT
- Title: SweRank+: Multilingual, Multi-Turn Code Ranking for Software Issue Localization
- Authors: Revanth Gangi Reddy, Ye Liu, Wenting Zhao, JaeHyeok Doo, Tarun Suresh, Daniel Lee, Caiming Xiong, Yingbo Zhou, Semih Yavuz, Shafiq Joty,
- Abstract summary: SweRank+ is 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.<n>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.
- Score: 85.2081165593314
- License: http://creativecommons.org/licenses/by/4.0/
- 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.
Related papers
- What Drives Cross-lingual Ranking? Retrieval Approaches with Multilingual Language Models [0.19116784879310025]
Cross-lingual information retrieval is challenging due to disparities in resources, scripts, and weak cross-lingual semantic alignment in embedding models.<n>Existing pipelines often rely on translation and monolingual retrievals, which add computational overhead and noise, performance.<n>This work systematically evaluates four intervention types, namely document translation, multilingual dense retrieval with pretrained encoders, contrastive learning at word, phrase, and query-document levels, and cross-encoder re-ranking, across three benchmark datasets.
arXiv Detail & Related papers (2025-11-24T17:17:40Z) - SweRank: Software Issue Localization with Code Ranking [109.3289316191729]
SweRank is an efficient retrieve-and-rerank framework for software issue localization.<n>We construct SweLoc, a large-scale dataset curated from public GitHub repositories.<n>We show that SweRank achieves state-of-the-art performance, outperforming both prior ranking models and costly agent-based systems.
arXiv Detail & Related papers (2025-05-07T19:44:09Z) - RAMQA: A Unified Framework for Retrieval-Augmented Multi-Modal Question Answering [9.915889321513678]
RAMQA is a unified framework combining learning-to-rank methods with generative permutation-enhanced ranking techniques.<n>Our generative ranking model generates re-ranked document IDs and specific answers from document candidates in various permutations.
arXiv Detail & Related papers (2025-01-23T00:50:33Z) - CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution [50.1875460416205]
The CRUXEVAL-X code reasoning benchmark contains 19 programming languages.<n>It comprises at least 600 subjects for each language, along with 19K content-consistent tests in total.<n>Even a model trained solely on Python can achieve at most 34.4% Pass@1 in other languages.
arXiv Detail & Related papers (2024-08-23T11:43:00Z) - AGRaME: Any-Granularity Ranking with Multi-Vector Embeddings [53.78802457488845]
We introduce the idea of any-granularity ranking, which leverages multi-vector embeddings to rank at varying levels of granularity.
We demonstrate the application of proposition-level ranking to post-hoc citation addition in retrieval-augmented generation.
arXiv Detail & Related papers (2024-05-23T20:04:54Z) - Unsupervised Multilingual Dense Retrieval via Generative Pseudo Labeling [32.10366004426449]
This paper introduces UMR, an Unsupervised dense Multilingual Retriever trained without any paired data.
We propose a two-stage framework which iteratively improves the performance of multilingual dense retrievers.
arXiv Detail & Related papers (2024-03-06T07:49:06Z) - Zero-Shot Listwise Document Reranking with a Large Language Model [58.64141622176841]
We propose Listwise Reranker with a Large Language Model (LRL), which achieves strong reranking effectiveness without using any task-specific training data.
Experiments on three TREC web search datasets demonstrate that LRL not only outperforms zero-shot pointwise methods when reranking first-stage retrieval results, but can also act as a final-stage reranker.
arXiv Detail & Related papers (2023-05-03T14:45:34Z) - On Cross-Lingual Retrieval with Multilingual Text Encoders [51.60862829942932]
We study the suitability of state-of-the-art multilingual encoders for cross-lingual document and sentence retrieval tasks.
We benchmark their performance in unsupervised ad-hoc sentence- and document-level CLIR experiments.
We evaluate multilingual encoders fine-tuned in a supervised fashion (i.e., we learn to rank) on English relevance data in a series of zero-shot language and domain transfer CLIR experiments.
arXiv Detail & Related papers (2021-12-21T08:10:27Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.