Research

Paper

AI LLM March 09, 2026

Human-AI Collaboration for Scaling Agile Regression Testing: An Agentic-AI Teammate from Manual to Automated Testing

Authors

Moustapha El Outmani, Manthan Venkataramana Shenoy, Ahmad Hatahet, Andreas Rausch, Tim Niklas Kniep, Thomas Raddatz, Benjamin King

Abstract

Agile organizations increasingly rely on automated regression testing to sustain rapid, high-quality software delivery. However, as systems grow and requirements evolve, a persistent bottleneck arises: test specifications are produced faster than they can be transformed into executable scripts, leading to mounting manual effort and delayed releases. In partnership with Hacon (a Siemens company), we present an agentic AI approach that generates system-level test scripts directly from validated specifications, aiming to accelerate automation without sacrificing human oversight. Our solution features a retrieval-augmented, multi-agent architecture integrated into Hacon's agile workflows. We evaluate this system through a mixed-method analysis of industrial artifacts and practitioner feedback. Results show that the AI teammate significantly increases test script throughput and reduces manual authoring effort, while underscoring the ongoing need for clear specifications and human review to ensure quality and maintainability. We conclude with practical lessons for scaling regression automation and fostering effective Human-AI collaboration in agile environments.

Metadata

arXiv ID: 2603.08190
Provider: ARXIV
Primary Category: cs.SE
Published: 2026-03-09
Fetched: 2026-03-10 05:43

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.08190v1</id>\n    <title>Human-AI Collaboration for Scaling Agile Regression Testing: An Agentic-AI Teammate from Manual to Automated Testing</title>\n    <updated>2026-03-09T10:19:13Z</updated>\n    <link href='https://arxiv.org/abs/2603.08190v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.08190v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Agile organizations increasingly rely on automated regression testing to sustain rapid, high-quality software delivery. However, as systems grow and requirements evolve, a persistent bottleneck arises: test specifications are produced faster than they can be transformed into executable scripts, leading to mounting manual effort and delayed releases. In partnership with Hacon (a Siemens company), we present an agentic AI approach that generates system-level test scripts directly from validated specifications, aiming to accelerate automation without sacrificing human oversight. Our solution features a retrieval-augmented, multi-agent architecture integrated into Hacon's agile workflows. We evaluate this system through a mixed-method analysis of industrial artifacts and practitioner feedback. Results show that the AI teammate significantly increases test script throughput and reduces manual authoring effort, while underscoring the ongoing need for clear specifications and human review to ensure quality and maintainability. We conclude with practical lessons for scaling regression automation and fostering effective Human-AI collaboration in agile environments.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.SE'/>\n    <published>2026-03-09T10:19:13Z</published>\n    <arxiv:comment>Preprint submitted to the Human-AI Collaboration in Agile Teams Workshop at the 27th International Conference on Agile Software Development (XP 2026)</arxiv:comment>\n    <arxiv:primary_category term='cs.SE'/>\n    <author>\n      <name>Moustapha El Outmani</name>\n    </author>\n    <author>\n      <name>Manthan Venkataramana Shenoy</name>\n    </author>\n    <author>\n      <name>Ahmad Hatahet</name>\n    </author>\n    <author>\n      <name>Andreas Rausch</name>\n    </author>\n    <author>\n      <name>Tim Niklas Kniep</name>\n    </author>\n    <author>\n      <name>Thomas Raddatz</name>\n    </author>\n    <author>\n      <name>Benjamin King</name>\n    </author>\n  </entry>"
}