Scholarlink

This paper presents CoverNexus, a novel multi-agent system leveraging Large Language Models (LLMs) to improve code coverage through automated unit test generation. We introduce a flexible architecture combining LLMs with specialized testing components, outperforming existing methods in coverage and correctness. Our approach is evaluated using CoverBench, a new benchmark derived from HumanEval, tailored for assessing test generation and coverage improvement. Comprehensive experiments demonstrate CoverNexus’s superiority, with GPT-4 achieving 99.91% coverage and 77.44% correctness in multi-agent setups. We observe that closed-source models excel in multi-agent configurations, while open-source models perform better in single-agent scenarios. This work provides valuable insights into the trade-offs between coverage and correctness, contributing to the advancement of AI-assisted software testing and more efficient software development processes.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

CoverNexus: Multi-agent LLM System for Automated Code Coverage Enhancement

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Thiem Nguyen Ba,
  • Binh Nguyen Thanh,
  • Viet-Trung Tran

摘要

This paper presents CoverNexus, a novel multi-agent system leveraging Large Language Models (LLMs) to improve code coverage through automated unit test generation. We introduce a flexible architecture combining LLMs with specialized testing components, outperforming existing methods in coverage and correctness. Our approach is evaluated using CoverBench, a new benchmark derived from HumanEval, tailored for assessing test generation and coverage improvement. Comprehensive experiments demonstrate CoverNexus’s superiority, with GPT-4 achieving 99.91% coverage and 77.44% correctness in multi-agent setups. We observe that closed-source models excel in multi-agent configurations, while open-source models perform better in single-agent scenarios. This work provides valuable insights into the trade-offs between coverage and correctness, contributing to the advancement of AI-assisted software testing and more efficient software development processes.