InfCode-C++: Intent-Guided Semantic Retrieval and AST-Structured Search for C++ Issue Resolution
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912720313384960 |
|---|---|
| author | Dong, Qingao Wang, Mengfei Zhang, Hengzhi Li, Zhichao Yuan, Yuan Li, Mu Gao, Xiang Sun, Hailong Hu, Chunming Lv, Weifeng |
| author_facet | Dong, Qingao Wang, Mengfei Zhang, Hengzhi Li, Zhichao Yuan, Yuan Li, Mu Gao, Xiang Sun, Hailong Hu, Chunming Lv, Weifeng |
| contents | Large language model (LLM) agents have recently shown strong performance on repository-level issue resolution, but existing systems are almost exclusively designed for Python and rely heavily on lexical retrieval and shallow code navigation. These approaches transfer poorly to C++ projects, where overloaded identifiers, nested namespaces, template instantiations, and deep control-flow structures make context retrieval and fault localization substantially more difficult. As a result, state-of-the-art Python-oriented agents show a drastic performance drop on the C++ subset of MultiSWE-bench. We introduce INFCODE-C++, the first C++-aware autonomous system for end-to-end issue resolution. The system combines two complementary retrieval mechanisms -- semantic code-intent retrieval and deterministic AST-structured querying -- to construct accurate, language-aware context for repair.These components enable precise localization and robust patch synthesis in large, statically typed C++ repositories. Evaluated on the \texttt{MultiSWE-bench-CPP} benchmark, INFCODE-C++ achieves a resolution rate of 25.58\%, outperforming the strongest prior agent by 10.85 percentage points and more than doubling the performance of MSWE-agent. Ablation and behavioral studies further demonstrate the critical role of semantic retrieval, structural analysis, and accurate reproduction in C++ issue resolution. INFCODE-C++ highlights the need for language-aware reasoning in multi-language software agents and establishes a foundation for future research on scalable, LLM-driven repair for complex, statically typed ecosystems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_16005 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | InfCode-C++: Intent-Guided Semantic Retrieval and AST-Structured Search for C++ Issue Resolution Dong, Qingao Wang, Mengfei Zhang, Hengzhi Li, Zhichao Yuan, Yuan Li, Mu Gao, Xiang Sun, Hailong Hu, Chunming Lv, Weifeng Software Engineering Artificial Intelligence Large language model (LLM) agents have recently shown strong performance on repository-level issue resolution, but existing systems are almost exclusively designed for Python and rely heavily on lexical retrieval and shallow code navigation. These approaches transfer poorly to C++ projects, where overloaded identifiers, nested namespaces, template instantiations, and deep control-flow structures make context retrieval and fault localization substantially more difficult. As a result, state-of-the-art Python-oriented agents show a drastic performance drop on the C++ subset of MultiSWE-bench. We introduce INFCODE-C++, the first C++-aware autonomous system for end-to-end issue resolution. The system combines two complementary retrieval mechanisms -- semantic code-intent retrieval and deterministic AST-structured querying -- to construct accurate, language-aware context for repair.These components enable precise localization and robust patch synthesis in large, statically typed C++ repositories. Evaluated on the \texttt{MultiSWE-bench-CPP} benchmark, INFCODE-C++ achieves a resolution rate of 25.58\%, outperforming the strongest prior agent by 10.85 percentage points and more than doubling the performance of MSWE-agent. Ablation and behavioral studies further demonstrate the critical role of semantic retrieval, structural analysis, and accurate reproduction in C++ issue resolution. INFCODE-C++ highlights the need for language-aware reasoning in multi-language software agents and establishes a foundation for future research on scalable, LLM-driven repair for complex, statically typed ecosystems. |
| title | InfCode-C++: Intent-Guided Semantic Retrieval and AST-Structured Search for C++ Issue Resolution |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2511.16005 |