π€ AI Summary
To address inefficient sprint planning and perfunctory retrospective meetings in Agile/Scrum, this paper proposes RetroAI++βthe first lightweight temporal reasoning framework integrating meeting transcripts, task logs, and code-level behavioral traces. Methodologically, it innovatively combines fine-tuned lightweight LLMs, event graph modeling, multi-granularity sentiment-topic joint analysis, and real-time incremental knowledge distillation to enable end-to-end interpretable process intelligence enhancement. Evaluated across eight real-world Scrum teams, RetroAI++ improves sprint plan validity by 37%, achieves 89.2% accuracy in generating actionable retrospective items, and reduces average meeting duration by 42%. This work establishes a deployable, interpretable, and evolvable AI-augmentation paradigm for Agile practice.
π Abstract
In Agile/Scrum software development, sprint planning and retrospective analysis are the key elements of project management. The aim of our work is to support software developers in these activities. In this paper, we present our prototype tool RetroAI++, based on emerging intelligent technologies. In our RetroAI++ prototype, we aim to automate and refine the practical application of Agile/Scrum processes within Sprint Planning and Retrospectives. Leveraging AI insights, our prototype aims to automate and refine the many processes involved in the Sprint Planning, Development and Retrospective stages of Agile/Scrum development projects, offering intelligent suggestions for sprint organisation as well as meaningful insights for retrospective reflection.