# Athena: Intermediate Representations for Iterative Scaffolded App Generation with an LLM

## TL;DR

Athena introduces an iterative app generation environment using shared intermediate representations to improve the quality, organization, and usability of code generated by LLMs for complex user interfaces.

## Contribution

It presents Athena, a novel environment that leverages shared intermediate representations to scaffold and organize LLM-generated code for complete user interfaces.

## Key findings

- 75% of participants preferred Athena over baseline methods
- Intermediate representations improve code organization and error reduction
- Supports iterative development of complex UIs with LLMs

## Abstract

It is challenging to generate the code for a complete user interface using a Large Language Model (LLM). User interfaces are complex and their implementations often consist of multiple, inter-related files that together specify the contents of each screen, the navigation flows between the screens, and the data model used throughout the application. It is challenging to craft a single prompt for an LLM that contains enough detail to generate a complete user interface, and even then the result is frequently a single large and difficult to understand file that contains all of the generated screens. In this paper, we introduce Athena, a prototype application generation environment that demonstrates how the use of shared intermediate representations, including an app storyboard, data model, and GUI skeletons, can help a developer work with an LLM in an iterative fashion to craft a complete user interface. These intermediate representations also scaffold the LLM's code generation process, producing organized and structured code in multiple files while limiting errors. We evaluated Athena with a user study that found 75% of participants preferred our prototype over a typical chatbot-style baseline for prototyping apps.