arXiv cs.AI· Jonathan Ullrich, Julien Siebert, Michael Kl\"as, Adam Trendowicz, Andreas Jedlitschka·· 2 小时前AI 评分23
智能体轨迹作为软件质量保证的证据:arXiv 论文提出分析方法
Agent Trajectories as Evidence for Software Quality Assurance
AI 导读
一篇提交至 ICSE2027 AMPLIFY Workshop 的论文提出,将自主软件智能体的可观测轨迹连同软件与智能体规范、AI 生成的制品一起作为证据,用于有针对性的质量保证。其目标是优先审查关键决策,调查其对软件问题的可能影响,并改进规范与开发实践。论文同时指出,仅凭轨迹无法证明决策合理或修正有效,并探讨何时更简单的 QA 方法已经足够。
正文 · 原文
Abstract:Autonomous software agents increasingly plan, implement, and test software with limited human oversight. Their decisions may introduce implicit assumptions that final code and passing tests do not adequately expose. We propose analyzing observable agent trajectories alongside software and agent specifications and AI generated artifacts as evidence for targeted quality assurance. The aim is to prioritize consequential decisions for scrutiny, investigate their possible contribution to software problems, and inform improvements to specifications and development practices. Industrial experience motivates the idea; available execution records and preliminary analysis methods make it plausible. However, trajectories alone do not establish that decisions are justified, outcomes acceptable, or corrective changes effective. We ask how this evidence can support review, diagnosis, and continuous quality improvement, and when simpler QA approaches suffice. Perspectives from requirements engineering, verification and validation, agent systems, causal inference, empirical software engineering, and human factors could help develop and evaluate the idea.
| Comments: | 3 pages, submitted to ICSE2027 AMPLIFY Workshop this https URL |
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI) |
| ACM classes: | D.2.0 |
| Cite as: | arXiv:2611.22323 [cs.SE] |
| (or arXiv:2611.22323v1 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2611.22323 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Julien Siebert [view email]
[v1]
Tue, 17 Nov 2026 07:22:29 UTC (84 KB)
来源:arXiv cs.AI · arxiv.org