Reproduce “AI and Agile Software Development: A Research Roadmap from the XP2025 Workshop” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Zheying Zhang, Tomas Herda, Victoria Pichler, Pekka Abrahamsson, Geir K. Hanssen, Joshua Kerievsky, Alex Polyakov, Mohit Chandna and 15 more

The XP2025 workshop synthesizes practitioner and researcher insights into a research roadmap for integrating Generative AI into agile software development. It identifies six key frustrations experienced by agile teams and proposes five interconnected research themes with short-term actions and long-term directions to guide human-centered AI adoption.

Key insights

  • Practitioners experience a "socio-technical gap" where AI tooling outpaces organizational practices and human skills, manifested in six categories of frustrations, with "lack of prompting skills" being the most voted.
  • Integrating Generative AI into agile software development requires a human-centered approach that transitions from viewing AI as mere assistants to integrated, context-aware teammates.
  • Successful AI-agile integration depends not only on technical solutions but also on addressing governance, fostering AI literacy, designing for creativity, and establishing clear value realization frameworks.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.