SecCodeBench is a benchmark suite for evaluating the security of AI-generated code, specifically designed for modern Agentic Coding Tool. It is jointly developed by Alibaba Group in collaboration with ...

Abstract: With the rapid development of ubiquitous computing, the demand for efficient software development is growing stronger. Code reuse is an effective means to enhance software development ...

Abstract: While large language models (LLMs) have demonstrated the ability to generate hardware description language (HDL) code for digital circuits, they still face the hallucination problem, which ...

read_file: Read file contents with flexible line range control edit_file: Make precise edits to files with clear instructions Supports complete file replacement ...