一句话：从数据质量、模型架构与推理能力三方面提升代码语言模型，提出CODA、CodeDenoise、LEAM/LEAM++、μFiX和Specine。
现有语言模型在复杂编程场景中仍受限于代码数据质量、模型架构和推理能力。该研究通过三条互补路径系统应对这些问题：第一，用代码差异引导的对抗增强技术CODA和代码去噪技术CodeDenoise提升代码数据质量；第二，用语法引导的代码语言模型LEAM和LEAM++改进模型架构；第三，用提示技术μFiX和基于智能体的技术Specine增强模型推理能力。这些技术旨在促进语言模型在软件开发中的实际采用，并推动智能软件工程的发展。摘要未给出具体的基准、实验设置与量化结果。
Recent advances in language models (LMs) have driven significant progress in various software engineering tasks. However, existing LMs still struggle with complex programming scenarios due to limitations in data quality, model architecture, and reasoning capability. This research systematically addresses these challenges through three complementary directions: (1) improving code data quality with a code difference-guided adversarial augmentation technique (CODA) and a code denoising technique (CodeDenoise); (2) enhancing model architecture via syntax-guided code LMs (LEAM and LEAM++); and (3) advancing model reasoning with a prompting technique (μ FiX) and an agent-based technique (Specine). These techniques aim to promote the practical adoption of LMs in software development and further advance intelligent software engineering.