SweRank: Software Issue Localization with Code Ranking

By Revanth Gangi Reddy, Tarun Suresh, Jae Doo, Ye Liu, Xuan-Phi Nguyen, Ying-Bo Zhou, Semih Yavuz, Caiming Xiong, Heng Ji, Shafiq Joty. 2025

Subfields: Information Retrieval & Search, Program Analysis & Verification, Software Engineering

Citations in the corpus

• SweRank+: Multilingual, Multi-Turn Code Ranking for Software Issue Localization (2025, unknown): “To improve efficiency, S WE R-ANK (Reddy et al., 2025) reformulates issue localization as a retrieve-and-rerank problem, leveraging specialized bi-encoder retrievers and LLM rerankers trained on curated datasets (Suresh et al., 2024).”
• A Benchmark for Localizing Code and Non-Code Issues in Software Projects (2025, unknown): “Moreover, they are widely adopted and acknowledged by recent studies in software engineering, demonstrating strong reasoning capabilities and retrieval-augmented performance in similar scenarios Chen et al. (2025); Xia et al. (2024); Jimenez et al.; Reddy et al. (2025).”
• A^2Agent: Action-Aware Reinforcement Learning for Repository-Level Code Localization Agents (2026, unknown): “Early works in repository-level code localization rank files by similarity to the issue description using BM25 (Robertson and Zaragoza, 2009) or dense retrieval (Reddy et al., 2025; Suresh et al., 2025).”
• SHERLOC: Structured Diagnostic Localization for Code Repair Agents (2026, unknown): “Most localization methods retrieve faulty files and functions [Zhou et al., 2012, Reddy et al., 2025, Yu et al., 2025]; some (e.g., OrcaLoca, SWE-Debate [Li et al., 2025]) also produce free-form report text.”
• CORE-Bench: A Comprehensive Benchmark for Code Retrieval in the Era of Agentic Coding (2026, unknown): “5B-instruct (Li et al., 2023), Qwen3-Embedding (Zhang et al., 2025), E5-Mistral (Wang et al., 2024a), F2LLM-v2 (Zhang et al., 2026), CodeRankEmbed (Suresh et al., 2025), Jina Code Embeddings (Kryvosheieva et al., 2025), C2LLM-7B (Qin et al., 2025), SweRankEmbed-Large (Reddy et al., 2025), and our in”
• GraphLocator: Graph-Guided Causal Reasoning for Issue Localization (2025, unknown): “Each component, from search tools to priority-driven graph expansion, and graph-guided reasoning, directly enables effective localization.”
• Agentic Software Issue Resolution with Large Language Models: A Survey (2025, unknown): “Fine-tuning-based approaches fall into two categories: fine-tuning generation models and fine-tuning embedding models.”
• SpIDER: Spatially Informed Dense Embedding Retrieval for Software Issue Localization (2025, unknown): “To address this gap, Fehr et al. (2025) and Reddy et al. (2025) introduce bimodal encoders fine-tuned on GitHub-style issue resolution datasets such as SWEBench (Jimenez et al., 2024), resulting in improved alignment between issue and code representations.”