11 papers · 1 filter
Beyond Repository Boundaries: Cross-Repository Graph Retrieval for Code Generation
Minh Le-Anh, Nam Le Hai, Quyen Tran +4
Repository-level code generation requires generated code to be compatible not only with the target repository but also with its dependency environment. Existing retrieval-based met…
XAgent: eXecution-guided Agentic AI for Effective Localization and Resolution of GitHub Issues
Hieu Huynh, Patanamon Thongtanunam, Michael Fu +2
Agentic AI has enabled capabilities in leveraging Large Language Models (LLMs) to autonomously resolve repository-level GitHub issues. However, due to the reliance on limited stati…
A Single Patch Is Not Enough: Deterministic Fusion of Repair Candidates
Boyang Yang, Xiangliang Hu, Luyao Ren +4
Modern LLM coding agents are commonly evaluated using pass@k, but developers typically apply a single final patch in real-world settings. This pass@k-to-pass@1 gap is a post-genera…
Documentation-Guided Agentic Codebase Migration from C to Rust
Minh Le-Anh, Anh Nguyen Hoang, Bach Le +1
Migrating legacy C repositories to Rust promises stronger memory safety, but existing translators often work at the level of files or functions and miss architectural intent. We pr…
Beyond Localization: Recoverable Headroom and Residual Frontier in Repository-Level RAG-APR
Pengtao Zhao, Boyang Yang, Bach Le +2
Repository-level automated program repair (APR) increasingly treats stronger localization as the main path to better repair. We ask a more targeted question: once localization is s…
Do Not Treat Code as Natural Language: Implications for Repository-Level Code Generation and Beyond
Minh Le-Anh, Huyen Nguyen, Khanh An Tran +4
Large language models for code (CodeLLMs) have demonstrated remarkable success in standalone code completion and generation, sometimes even surpassing human performance, yet their…