Beyond Function-Level Search: Repository-Aware Dual-Encoder Code Retrieval with Adversarial Verification

2025-10-16 · Aofan Liu, Shiyuan Song, Haoxuan Li, Cehao Yang, Yiyan Qi arxiv

The escalating complexity of modern codebases has intensified the need for retrieval systems capable of interpreting cross-component change intents, a capability fundamentally absent in conventional function-level search paradigms. While recent studies have improved the alignment between natural language queries and code snippets, retrieving contextually relevant code for specific change requests remains largely underexplored. To address this gap, we introduce RepoAlign-Bench, the first benchmark specifically designed to evaluate repository-level code retrieval under change request driven scenarios, encompassing 52k annotated instances. This benchmark shifts the retrieval paradigm from function-centric matching to holistic repository-level reasoning. Furthermore, we propose ReflectCode, an adversarial reflection augmented dual-tower architecture featuring disentangled code_encoder and doc_encoder components. ReflectCode dynamically integrates syntactic patterns, function dependencies, and semantic expansion intents through large language model guided reflection. Comprehensive experiments demonstrate that ReflectCode achieves 12.2% improvement in Top-5 Accuracy and 7.1% in Recall over state-of-the-art baselines, establishing a new direction for context-aware code retrieval.

📄 PDF Abstract BibTeX arXiv:2510.24749

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language Queries

BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?

2026-03-03 · Guoxin Chen, Fanzhe Meng, Jiale Zhao, Minghao Li 외 arxiv

Current code-agent benchmarks primarily evaluate localized issue resolution within a single target repository, leaving under-tested many software engineering tasks that require external knowledge or broader repository-le…

Code Summarization Beyond Function Level

2025-02-23 · Vladimir Makharev, Vladimir Ivanov

Code summarization is a critical task in natural language processing and software engineering, which aims to generate concise descriptions of source code. Recent advancements have improved the quality of these summaries,…

Code Summarization Few-Shot Learning In-Context Learning Prompt Engineering+1

Toward Executable Repository-Level Code Generation via Environment Alignment

2026-04-04 · Ruwei Pan, Junlei Shen, Linhao Wu, Yueheng Zhu 외 arxiv

Large language models (LLMs) have achieved strong performance on code generation, but existing methods still struggle with repository-level code generation under executable validation. Under this evaluation setting, succ…

Code Generation

Beyond Code Snippets: Benchmarking LLMs on Repository-Level Question Answering

2026-03-27 · Yoseph Berhanu Alebachew, Hunter Leary, Swanand Vaishampayan, Chris Brown arxiv

Large Language Models (LLMs) have shown impressive capabilities across software engineering tasks, including question answering (QA). However, most studies and benchmarks focus on isolated functions or single-file snippe…

Question Answering

Beyond "What to Retrieve": Uncertainty in Retrieval-Augmented Code Generation

2026-07-27 · Chandan Kumar Sah, Li Zhang, Xiaoli Lian arxiv

Repository-level code generation relies on heterogeneous evidence whose relevance, compatibility, and completeness are inherently uncertain. Similar-code examples, repository context, and project-specific APIs may provid…