Skip to content

AI and Agile Software Development: From Frustration to Success - XP2025 Workshop Summary

Jun 2025 · XP Workshops · pp. 3-13 · 3 citations · 11 references
Computer Science

TL;DR

The workshop culminated in the collaborative development of a research roadmap that pinpoints actionable directions for future work, including both immediate solutions and ambitious long-term goals.

Abstract

The full-day workshop on AI and Agile at XP 2025 convened a diverse group of researchers and industry practitioners to address the practical challenges and opportunities of integrating Artificial Intelligence into Agile software development. Through interactive sessions, participants identified shared frustrations related to integrating AI into Agile Software Development practices, including challenges with tooling, governance, data quality, and critical skill gaps. These challenges were systematically prioritized and analyzed to uncover root causes. The workshop culminated in the collaborative development of a research roadmap that pinpoints actionable directions for future work, including both immediate solutions and ambitious long-term goals. The key outcome is a structured agenda designed to foster joint industry-academic efforts to move from identified frustrations to successful implementation.

Read PDF

Similar papers

Open access 2026

Programming Methodologies: Agile, Scrum, and Devops in Practice

This study highlights how these methodologies complement each other in practice, improve software quality, reduce time-to-market, and enhance collaboration among stakeholders in modern software engineering environments.

Nkiwa Monkila Jonathan, Monkila Nkiwa Barthelemy, Padinganyi Tshiombela Faustin et al. · 0 citations
Review

Development Activities: Perspectives of Agile Practitioners

This study investigates Agile practitioners’ perceptions of collaborating with GenAI in software development activities and findings advance the understanding of human-AI collaboration in Agile settings and can guide both future research and the practical adoption of GenAI in Agile environments.

Daniel Planötscher, Xiaofeng Wang, Mahum Adil et al. · 0 citations
Review Aug 2026

Operationalizing the EU AI Act in Agile Software Development: A Guideline-Based Approach

An evaluated guideline that operationalizes EU AI Act obligations as activities integrable into existing agile practice is provided: an evaluated guideline that operationalizes EU AI Act obligations as activities integrable into existing agile practice.

D. Schrader, Eva-Maria Schön, Henning Fritzemeier et al. · 0 citations
Review Open access Aug 2026

Software Development Methodologies Evolutionary Trends from Waterfall to DevOps

It was identified that the industry tends to follow a hybrid Agile-DevOps practice with more emphasis on automation, continuous integration and collaboration to achieve quick and competitive software environments.

Raman Kumar · 0 citations
Review Open access Jul 2026

A Comprehensive Systematic Literature Review of Agile Methodology

A literature review of Agile methodologies from 2001 to 2025 is presented, systematically examining their evolution, cross-sectoral diffusion, and key adaptations, and identifies critical gaps in the literature and outlines future research directions.

Majid Al-Nabae, Norshahrizan Nordin, Abdulwadod S. A. Hassan et al. · 0 citations
Open access 2018

Combining Low-Code Platforms with Traditional Software Engineering for Agile Development

This paper explores the synergies between low-code platforms and traditional development methodologies, proposing a hybrid model that leverages the strengths of both to improve development efficiency and product quality.

Ajay Krishnan, Ritu Agarwal · 0 citations

Related blog posts

Microsoft Research Blog Oct 6, 2026

What AI gets wrong and what failure teaches us

Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity.  The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.

Microsoft Research Blog Jul 30, 2026

Echoverse: Deep, evolving environments for computer-use agents

Computer-use AI agents struggle with multi-step workflows like email and customer support. Echoverse trains agents in realistic environments rather than simply providing more training tasks, helping them improve as the tasks, tests, and environments evolve. The post Echoverse: Deep, evolving environments for computer-use agents appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.