mlsanityData to 14 Oct 2026

Beyond Prototyping: Autonomous, Enterprise-Grade Frontend Development from Pixel to Production via a Specialized Multi-Agent Framework

arXiv 2512.06046 ↗First posted 5 Dec 2025cs.SE cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

We present AI4UI, a framework of autonomous front-end development agents purpose-built to meet the rigorous requirements of enterprise-grade application delivery. Unlike general-purpose code assistants designed for rapid prototyping, AI4UI focuses on production readiness delivering secure, scalable, compliant, and maintainable UI code integrated seamlessly into enterprise workflows. AI4UI operates with targeted human-in-the-loop involvement: at the design stage, developers embed a Gen-AI-friendly grammar into Figma prototypes to encode requirements for precise interpretation; and at the post processing stage, domain experts refine outputs for nuanced design adjustments, domain-specific optimizations, and compliance needs. Between these stages, AI4UI runs fully autonomously, converting designs into engineering-ready UI code. Technical contributions include a Figma grammar for autonomous interpretation, domain-aware knowledge graphs, a secure abstract/package code integration strategy, expertise driven architecture templates, and a change-oriented workflow coordinated by specialized agent roles. In large-scale benchmarks against industry baselines and leading competitor systems, AI4UI achieved 97.24% platform compatibility, 87.10% compilation success, 86.98% security compliance, 78.00% feature implementation success, 73.50% code-review quality, and 73.36% UI/UX consistency. In blind preference studies with 200 expert evaluators, AI4UI emerged as one of the leaders demonstrating strong competitive standing among leading solutions. Operating asynchronously, AI4UI generates thousands of validated UI screens in weeks rather than months, compressing delivery timeline

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 52 references that are in the map. First posted on arXiv 5 Dec 2025.

Builds on

16 of 52 references.

References · 16

  1. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  3. 2017Deep reinforcement learning from human preferencescited by 3,912
  4. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,998
  5. 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preferencecited by 1,184
  6. 2024Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluatorscited by 897
  7. 2023AGIEval: A Human-Centric Benchmark for Evaluating Foundation Modelscited by 716
  8. 2024Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineeringcited by 152
  9. 2025A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Modelscited by 87
  10. 2025DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generationcited by 45
  11. 2024WebCode2M: A Real-World Dataset for Code Generation from Webpage Designscited by 44
  12. 2024Prototype2Code: End-to-end Front-end Code Generation from UI Design Prototypescited by 10
4 more
  1. 2024MAxPrototyper: A Multi-Agent Generation System for Interactive User Interface Prototypingcited by 6
  2. 2018Do we agree on user interface aesthetics of Android apps?cited by 3
  3. 2018How Content Volume on Landing Pages Influences Consumer Behaviorcited by 2
  4. 2019A gradual approach for maximising user conversion without compromising experience with high visual intensity website elementscited by 2

Built on by

Not cited yet.