Our paper “Human-AI Collaboration for Scaling Agile Regression Testing: An Agentic-AI Teammate from Manual to Automated Testing” has been accepted at XP 2026

The paper “Human-AI Collaboration for Scaling Agile Regression Testing: An Agentic-AI Teammate from Manual to Automated Testing” by Moustapha El Outmani, Manthan Venkataramana Shenoy, Ahmad Hatahet, Andreas Rausch, Tim Niklas Kniep, Thomas Raddatz and Benjamin King has been accepted at XP 2026, the 27^th International Conference on Agile Software Development. 

XP is the premier conference on agile software development, uniquely combining research and practice. It’s where researchers, practitioners, thought leaders, coaches, and trainers come together to share their latest innovations and insights.
Originally launched 26 years ago with a focus on eXtreme Programming, the XP conference has evolved to embrace all modern agile approaches and the broadening dimensions of agility. XP 2026 will take place in São Paulo, Brazil, from April 8 – 11, 2026.

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.

The full paper can be read at https://arxiv.org/abs/2603.08190