InfCode-C++: 基于意图的语义检索与AST结构化搜索用于C++问题解决
InfCode-C++: Intent-Guided Semantic Retrieval and AST-Structured Search for C++ Issue Resolution
AI总结：
INFCODE-C++ 是首个针对 C++ 的自主系统，通过结合语义代码意图检索和 AST 结构查询，实现端到端的问题解决，其性能显著优于现有方法。
摘要：
大型语言模型（LLM）代理最近在仓库级问题解决中表现出强劲的性能，但现有系统几乎 exclusively 为 Python 设计，依赖于词汇检索和浅层代码导航。这些方法在 C++ 项目中表现不佳，因为重载标识符、嵌套命名空间、模板实例化和深层控制流结构使上下文检索和故障定位显著更加困难。因此，最先进的 Python 面向代理在 MultiSWE-bench 的 C++ 子集上表现出急剧的性能下降。我们引入了 INFCODE-C++，这是第一个针对 C++ 的自主系统，用于端到端的问题解决。该系统结合了两种互补的检索机制--语义代码意图检索和确定性 AST 结构查询--以构建准确的、语言感知的上下文用于修复。这些组件使在大型、静态类型 C++ 仓库中实现精确的定位和稳健的补丁合成成为可能。在 \texttt{MultiSWE-bench-CPP} 基准上评估，INFCODE-C++ 实现了 25.58\% 的解决率，优于最强的先前代理 10.85 个百分点，且超过 MSWE-agent 的性能超过一倍。消融和行为研究进一步证明了语义检索、结构分析和准确重现在 C++ 问题解决中的关键作用。INFCODE-C++ 强调了多语言软件代理中语言感知推理的必要性，并为未来关于可扩展、LLM 驱动修复的复杂、静态类型生态系统的研究奠定了基础。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
