Related papers: RPG: A Repository Planning Graph for Unified and S…

Automated program repair (APR) struggles to scale from isolated functions to full repositories, as it demands a global, task-aware understanding to locate necessary changes. Current methods, limited by context and reliant on shallow…

Retrieval-augmented generation (RAG) empowers large language models to access external and private corpus, enabling factually consistent responses in specific domains. By exploiting the inherent structure of the corpus, graph-based RAG…

The code generation capabilities of Large Language Models (LLMs) have transformed the field of software development. However, this advancement also presents significant security challenges, as LLM-generated code often contains…

As code completion task from function-level to repository-level, leveraging contextual information from large-scale codebases becomes a core challenge. However, existing retrieval-augmented generation (RAG) methods typically treat code as…

Large language models (LLMs) commonly struggle with specialized or emerging topics which are rarely seen in the training corpus. Graph-based retrieval-augmented generation (GraphRAG) addresses this by structuring domain knowledge as a graph…

Real-world tasks require decisions at varying granularities, and humans excel at this by leveraging a unified cognitive representation where planning is fundamentally understood as a high-level form of action. However, current Large…

Paraphrase generation is an important task in natural language processing. Previous works focus on sentence-level paraphrase generation, while ignoring document-level paraphrase generation, which is a more challenging and valuable task. In…

Repository-level bug localization-the task of identifying where code must be modified to fix a bug-is a critical software engineering challenge. Standard Large Language Modles (LLMs) are often unsuitable for this task due to context window…

Large language models (LLMs) have achieved strong performance on code generation, but existing methods still struggle with repository-level code generation under executable validation. Under this evaluation setting, success is determined…

Scaling up executable code data is significant for improving language models' software engineering capability. The intricate nature of the process makes it labor-intensive, time-consuming and expert-knowledge-dependent to build a large…

Large language models (LLMs) have achieved strong performance in code generation, but most methods rely on autoregressive decoding without global planning, often leading to locally coherent yet globally suboptimal solutions (e.g., failing…

Recent advancements in Large Language Models (LLMs) have transformed code generation from natural language queries. However, despite their extensive knowledge and ability to produce high-quality code, LLMs often struggle with contextual…

Large Language Models (LLMs) excel at code generation but struggle with complex problems. Retrieval-Augmented Generation (RAG) mitigates this issue by integrating external knowledge, yet retrieval models often miss relevant context, and…

Despite the remarkable success of large language models (LLMs) on traditional natural language processing tasks, their planning ability remains a critical bottleneck in tackling complex multi-step reasoning tasks. Existing approaches mainly…

Large Language Models (LLMs) have recently shown remarkable progress in code generation, yet their ability to construct complete software repositories from scratch remains poorly understood. A fundamental bottleneck is the lack of…

Large Language Models (LLMs) excel in stand-alone code tasks like HumanEval and MBPP, but struggle with handling entire code repositories. This challenge has prompted research on enhancing LLM-codebase interaction at a repository scale.…

We introduce CRPE (Code Reasoning Process Enhancer), an innovative three-stage framework for data synthesis and model training that advances the development of sophisticated code reasoning capabilities in large language models (LLMs).…

Large Language Models (LLMs) have greatly advanced code auto-completion systems, with a potential for substantial productivity enhancements for developers. However, current benchmarks mainly focus on single-file tasks, leaving an assessment…

Maintainable and general software allows developers to build robust applications efficiently, yet achieving these qualities often requires refactoring specialized solutions into reusable components. This challenge becomes particularly…

Enterprise level software is implemented using multi-layer architecture. These layers are often implemented using de-coupled solutions with millions of lines of code. Programmers often have to track and debug a function call from user…