9 papers
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…
CREDENCE: Claim Reduction for Decomposition & Enhanced Credibility -- Semantic Metrics and Convergence Analysis
Phuong Huu Vu Tran, Thuan Duc Mai, Bach Xuan Le
Decomposing compound sentences into atomic, verifiable claims is a prerequisite for reliable automated fact-checking. Prior work has relied on token-overlap (Jaccard) metrics that…
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…
Unlocking LLM Repair Capabilities Through Cross-Language Translation and Multi-Agent Refinement
Wenqiang Luo, Jacky Wai Keung, Boyang Yang +4
Recent advances in leveraging LLMs for APR have demonstrated impressive capabilities in fixing software defects. However, current LLM-based approaches predominantly focus on mainst…
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…