Effort and Size Estimation in Software Projects with Large Language Model-based Intelligent Interfaces
This work addresses estimation difficulties for software developers using LLM interfaces, but it appears incremental as it builds on existing LLM applications in software design.
The paper tackles the challenge of estimating development effort when integrating LLM-based AI agents into software design, particularly for UI-based user stories, by proposing a method to enhance natural language specifications that accounts for data sources, interfaces, and algorithms, resulting in a comparison against traditional methods.
The advancement of Large Language Models (LLM) has also resulted in an equivalent proliferation in its applications. Software design, being one, has gained tremendous benefits in using LLMs as an interface component that extends fixed user stories. However, inclusion of LLM-based AI agents in software design often poses unexpected challenges, especially in the estimation of development efforts. Through the example of UI-based user stories, we provide a comparison against traditional methods and propose a new way to enhance specifications of natural language-based questions that allows for the estimation of development effort by taking into account data sources, interfaces and algorithms.