谁验证构建者？面向智能体生成软件的独立保障
原标题：Who Verifies the Builder? Toward Independent Assurance for Agent-Produced Software
AI 摘要
该论文指出，当编码智能体同时负责实现软件和编写测试时，通过的测试套件不再构成独立证据，因为测试会成为优化目标，代码、测试和预期输出可能共享同一误解。作者提出将构建平面与保障平面分离的框架，引入验证契约，并分两阶段验证：先做不接触实现的规格优先验证，再做实现感知验证（变异分析、属性测试、模糊测试），最终生成保障报告并将发布决策留给人类。在三个有状态服务上的预注册研究显示，构建者程序本身正确但自测遗漏了细微交互，新上下文中的验证者比构建者测试发现更多46个种子故障（Holm校正p=0.006），但另一提供商的验证者未增加检测。
正文节选
Who Verifies the Builder? Toward Independent Assurance for Agent-Produced Software Abstract Coding agents can now interpret a specification, implement it, write and execute tests, repair failures, and declare the result ready for release. When the same agentic system produces both the software and the evidence of its correctness, a passing test suite no longer constitutes independent evidence. Visible tests become an optimization target, code, tests, and oracles may share a single misinterpretat