Scrum Sprint Planning: LLM-based and algorithmic solutions

TL;DR

This paper explores the potential of Large Language Models like GPT-3.5 and GPT-4 for automating Scrum sprint planning, but finds current models do not yet produce sufficiently reliable results for practical use.

Contribution

It presents initial case studies evaluating LLMs for sprint planning, highlighting their limitations and the need for further development in this application area.

Findings

LLMs currently produce low-quality outputs for sprint planning

GPT-4 outperforms GPT-3.5 in initial tests

Further research is needed to improve model reliability

Abstract

Planning for an upcoming project iteration (sprint) is one of the key activities in Scrum planning. In this paper, we present our work in progress on exploring the applicability of Large Language Models (LLMs) for solving this problem. We conducted case studies with manually created data sets to investigate the applicability of OpenAI models for supporting the sprint planning activities. In our experiments, we applied three models provided OpenAI: GPT-3.5 Turbo, GPT-4.0 Turbo, and Val. The experiments demonstrated that the results produced by the models aren't of acceptable quality for direct use in Scrum projects.