# Automatically Generating Web Applications from Requirements Via Multi-Agent Test-Driven Development

arXiv: https://arxiv.org/abs/2509.25297 · HTML: https://mlsanity.com/paper/2509.25297/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 20 of its 58 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 20 of 20)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [pix2code: Generating Code from a Graphical User Interface Screenshot](https://mlsanity.com/paper/1705.07962/) (2017)
- [A Survey on Code Generation with LLM-based Agents](https://mlsanity.com/paper/2508.00083/) (2025)
- [Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity](https://mlsanity.com/paper/2507.09089/) (2025)
- [WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch](https://mlsanity.com/paper/2505.03733/) (2025)
- [Compilable Neural Code Generation with Compiler Feedback](https://mlsanity.com/paper/2203.05132/) (2022)
- [DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation](https://mlsanity.com/paper/2506.06251/) (2025)
- [Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training](https://mlsanity.com/paper/2508.00414/) (2025)
- [Make LLM a Testing Expert: Bringing Human-like Interaction to Mobile GUI Testing via Functionality-aware Decisions](https://mlsanity.com/paper/2310.15780/) (2023)
- [Machine Learning-Based Prototyping of Graphical User Interfaces for Mobile Apps](https://mlsanity.com/paper/1802.02312/) (2018)
- [Test-Driven Development for Code Generation](https://mlsanity.com/paper/2402.13521/) (2024)
- [ScreenCoder: Advancing Visual-to-Code Generation for Front-End Automation via Modular Multimodal Agents](https://mlsanity.com/paper/2507.22827/) (2025)
- [MRWeb: An Exploration of Generating Multi-Page Resource-Aware Web Code from UI Designs](https://mlsanity.com/paper/2412.15310/) (2024)
- [Bridging Design and Development with Automated Declarative UI Code Generation](https://mlsanity.com/paper/2409.11667/) (2024)
- [MLLM-Based UI2Code Automation Guided by UI Layout Information](https://mlsanity.com/paper/2506.10376/) (2025)
- [Automated Reporting of GUI Design Violations for Mobile Apps](https://mlsanity.com/paper/1802.04732/) (2018)
- [Vision-Based Mobile App GUI Testing: A Survey](https://mlsanity.com/paper/2310.13518/) (2023)
- [Classifying and Qualifying GUI Defects](https://mlsanity.com/paper/1703.09567/) (2017)
- [Write Your Own CodeChecker: An Automated Test-Driven Checker Development Approach with LLMs](https://mlsanity.com/paper/2411.06796/) (2024)

## Built on by (most cited first, 7 of 7)

- [Widget2Code: From Visual Widgets to UI Code via Multimodal LLMs](https://mlsanity.com/paper/2512.19918/) (2025)
- [Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence](https://mlsanity.com/paper/2606.15932/) (2026)
- [90% Faster, 100% Code-Free: MLLM-Driven Zero-Code 3D Game Development](https://mlsanity.com/paper/2509.26161/) (2025)
- [FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation](https://mlsanity.com/paper/2602.03798/) (2026)
- [TREAT: A Code LLMs Trustworthiness / Reliability Evaluation and Testing Framework](https://mlsanity.com/paper/2510.17163/) (2025)
- [Beyond Functional Correctness: Design Issues in AI IDE-Generated Large-Scale Projects](https://mlsanity.com/paper/2604.06373/) (2026)
- [Test-Driven Approaches to Software Engineering with Large Language Models: A Survey of Phases, Tasks, and Agent Skills](https://mlsanity.com/paper/2609.12012/) (2026)

## Abstract (arXiv)

Developing full-stack web applications is complex and time-intensive, demanding proficiency across diverse technologies and frameworks. Although recent advances in multimodal large language models (MLLMs) enable automated webpage generation from visual inputs, current solutions remain limited to front-end tasks and fail to deliver fully functional applications. In this work, we introduce TDDev, the first test-driven development (TDD)-enabled LLM-agent framework for end-to-end full-stack web application generation. Given a natural language description or design image, TDDev automatically derives executable test cases, generates front-end and back-end code, simulates user interactions, and iteratively refines the implementation until all requirements are satisfied. Our framework addresses key challenges in full-stack automation, including underspecified user requirements, complex interdependencies among multiple files, and the need for both functional correctness and visual fidelity. Through extensive experiments on diverse application scenarios, TDDev achieves a 14.4% improvement on overall accuracy compared to state-of-the-art baselines, demonstrating its effectiveness in producing reliable, high-quality web applications without requiring manual intervention.