用多智能体闭环系统让测试自动纠错，提升质量与覆盖率。
The Rise of Agentic Testing: Multi-Agent Systems for Robust Software Quality Assurance
- 三智能体协作：生成、执行分析、优化迭代
- 无效测试减少60%，覆盖率提升30%
- 适合追求自动化、高可靠性的研发团队
软件测试正迈向智能化自动化，但现有AI测试生成器仍存在输出静态、一次性的问题，常产生无效、冗余或无法执行的测试，缺乏执行反馈。本文提出一种代理式多模型测试框架，是一个闭环自校正系统：测试生成智能体、执行与分析智能体、评审与优化智能体协同工作，持续生成、执行、分析并优化测试直至收敛。通过沙箱执行、详细失败报告及对失败测试的迭代再生或修补，框架可自主提升测试质量并扩大覆盖范围。集成于兼容CI/CD的流水线中，利用覆盖率指标和执行结果作为强化信号引导优化。在基于微服务的应用上实证表明，相比单模型基线，无效测试减少60%，覆盖率提升30%，显著降低人工投入。结果表明，多智能体反馈驱动循环可将软件测试进化为自主、持续学习的质量保障生态，实现自修复、高可靠代码库。
原文摘要 · Abstract (English)
Software testing has progressed toward intelligent automation, yet current AI-based test generators still suffer from static, single-shot outputs that frequently produce invalid, redundant, or non-executable tests due to the lack of execution aware feedback. This paper introduces an agentic multi-model testing framework a closed-loop, self-correcting system in which a Test Generation Agent, an Execution and Analysis Agent, and a Review and Optimization Agent collaboratively generate, execute, analyze, and refine tests until convergence. By using sandboxed execution, detailed failure reporting, and iterative regeneration or patching of failing tests, the framework autonomously improves test quality and expands coverage. Integrated into a CI/CD-compatible pipeline, it leverages reinforcement signals from coverage metrics and execution outcomes to guide refinement. Empirical evaluations on microservice based applications show up to a 60% reduction in invalid tests, 30% coverage improvement, and significantly reduced human effort compared to single-model baselines demonstrating that multi-agent, feedback-driven loops can evolve software testing into an autonomous, continuously learning quality assurance ecosystem for self-healing, high-reliability codebases.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。