1
SwiftScale Software
用自然语言描述就能测试应用的QA智能体，告别繁琐脚本编写
QA agent that tests apps the way you'd explain them Discussion | Link
2
Clotho: Measuring Task-Specific Pre-Generation Test Adequacy for LLM Inputs
为LLM输入设计预生成测试充分性度量，Clotho让大模型测试有据可依
arXiv:2509.17314v4 Announce Type: replace-cross Abstract: Software increasingly relies on the emergent capabilities of Large Language Models (LLMs), f…
3
อวสาน QA อนาคตของอาชีพทดสอบซอฟต์แวร์ในยุค AI
AI能自动写测试，QA该何去何从？看懂这轮职业洗牌，抓住转型红利。
อวสาน QA? — อนาคตของอาชีพทดสอบซอฟต์แวร์ในยุค AI "AI เขียน test เองได้แล้ว — แล้ว QA จะอยู่ไปทำไม?" นี่คือคำถามที่ได้ยินบ่อยขึ้นทุกวันในวงการ tech — แล…
4
Ask HN: How are you using AI agents for testings features?
自改进QA代理处理超5亿tokens，开源实现如何重塑软件测试流程？
Hey, I am working on building agent-qa https://github.com/vostride/agent-qa which is a self-improving QA agent for software teams. Processed over 500M…
5
Audit AI-Generated Tests: Half of Green CI Proves Nothing
AI 生成的测试可能全绿却毫无价值，作者用真实实验拆穿 CI 绿灯的假象，教你审计测试有效性。
To audit AI-generated tests, score how many mirror the code instead of checking it. Green CI proves your tests agree with the code, not that it is cor…
6
Governance Controls for AI-Generated Test Artifacts in Autonomous Software Testing
AI生成测试工件的治理控制框架，为自主软件测试安全与合规提供体系化方案。
arXiv:2606.08806v1 Announce Type: cross Abstract: Artificial Intelligence (AI) and Large Language Models (LLMs) are increasingly used in autonomous so…
7
微软 Defender 表现垫底，香港消委会实测 24 款网络安全软件
香港消委会实测24款网络安全软件，微软Defender垫底，ESET和诺顿表现优异，值得关注。
IT之家 6 月 2 日消息，香港特别行政区消费者委员会于 5 月 28 日发布新一期《选择》月刊，对市面上适用于 Windows 和 macOS 操作系统的 24 款免费 / 收费网络安全软件进行全面比较测试，评估其整体防护性能、资源占用及易用程度。 据悉，本次测试由国际消费者研究及试验组织（IC…
8
AI based Software Testing system that works
主打真实可用的AI软件测试系统，一键自动化测试，提升开发效率。
Article URL: https://ytest.ai/ Comments URL: https://news.ycombinator.com/item?id=48360242 Points: 3 # Comments: 0
9
Multi-Agent LLM-based Metamorphic Testing for REST APIs
多智能体LLM协作实现REST API蜕变测试，创新技术获国际会议收录，自动化测试新思路。
arXiv:2605.28321v1 Announce Type: cross Abstract: As REST APIs become an increasingly significant part of software systems, their validation is becomi…
10
PBT-Bench: Benchmarking AI Agents on Property-Based Testing
首个聚焦属性基测试的AI基准，评估智能体从文档推导不变量并生成精确随机搜索策略的能力。
arXiv:2605.15229v1 Announce Type: cross Abstract: Existing code benchmarks measure whether an agent can produce any test that reproduces a known bug, …
11
AI-generated code that works – and proves it
AI生成代码靠得住？形式化方法给出数学级别的安全保障，从此告别“测试不能证明没有bug”的焦虑。
Article URL: https://www.codemetal.ai/research/ai-generated-code-that-works-and-proves-it Comments URL: https://news.ycombinator.com/item?id=48186334 …