# Computer-Use Agents as Judges for Generative User Interface

arXiv: https://arxiv.org/abs/2511.15567 · HTML: https://mlsanity.com/paper/2511.15567/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in GUI and mobile agents, one of 16 directions in LLM agents and tool use.
- Builds on 17 of its 21 references that are in the map.
- First posted on arXiv 19 Nov 2025.

## Placed in

- LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/)

## Builds on (most cited first, 17 of 17)

- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://mlsanity.com/paper/2401.01614/) (2024)
- [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022)
- [Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents](https://mlsanity.com/paper/2410.05243/) (2024)
- [WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?](https://mlsanity.com/paper/2403.07718/) (2024)
- [Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V](https://mlsanity.com/paper/2310.11441/) (2023)
- [Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction](https://mlsanity.com/paper/2412.04454/) (2024)
- [ShowUI: One Vision-Language-Action Model for GUI Visual Agent](https://mlsanity.com/paper/2411.17465/) (2024)
- [OmniParser for Pure Vision Based GUI Agent](https://mlsanity.com/paper/2408.00203/) (2024)
- [Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering](https://mlsanity.com/paper/2403.03163/) (2024)
- [pix2code: Generating Code from a Graphical User Interface Screenshot](https://mlsanity.com/paper/1705.07962/) (2017)
- [UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction](https://mlsanity.com/paper/2503.15661/) (2025)
- [VideoGUI: A Benchmark for GUI Automation from Instructional Videos](https://mlsanity.com/paper/2406.10227/) (2024)
- [UI Layout Generation with LLMs Guided by UI Grammar](https://mlsanity.com/paper/2310.15455/) (2023)

## Built on by (most cited first, 9 of 9)

- [Code2World: A GUI World Model via Renderable Code Generation](https://mlsanity.com/paper/2602.09856/) (2026)
- [Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond](https://mlsanity.com/paper/2604.22748/) (2026)
- [Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence](https://mlsanity.com/paper/2606.15932/) (2026)
- [Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation](https://mlsanity.com/paper/2605.30000/) (2026)
- [MaskClaw: Edge-Side Personalized Privacy Arbitration for GUI Agents with Behavior-Driven Skill Evolution](https://mlsanity.com/paper/2605.28646/) (2026)
- [VideoVIBE: A Video-Grounded Diagnostic Benchmark for One-Shot Interactive Website Generation](https://mlsanity.com/paper/2608.09573/) (2026)
- [Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction](https://mlsanity.com/paper/2606.29445/) (2026)
- [Quo Vadis, World Modeling?](https://mlsanity.com/paper/2608.02713/) (2026)
- [Automatic multimodal UX improvement recommendations from LLM agent user simulations](https://mlsanity.com/paper/2609.22971/) (2026)

## Abstract (arXiv)

Computer-Use Agents (CUA) are becoming increasingly capable of autonomously operating digital environments through Graphical User Interfaces (GUI). Yet, most GUI remain designed primarily for humans--prioritizing aesthetics and usability--forcing agents to adopt human-oriented behaviors that are unnecessary for efficient task execution. At the same time, rapid advances in coding-oriented language models (Coder) have transformed automatic GUI design. This raises a fundamental question: Can CUA as judges to assist Coder for automatic GUI design? To investigate, we introduce AUI-Gym, a benchmark for Automatic GUI development spanning 52 applications across diverse domains. Using language models, we synthesize 1560 tasks that simulate real-world scenarios. To ensure task reliability, we further develop a verifier that programmatically checks whether each task is executable within its environment. Building on this, we propose a Coder-CUA in Collaboration framework: the Coder acts as Designer, generating and revising websites, while the CUA serves as Judge, evaluating functionality and refining designs. Success is measured not by visual appearance, but by task solvability and CUA navigation success rate. To turn CUA feedback into usable guidance, we design a CUA Dashboard that compresses multi-step navigation histories into concise visual summaries, offering interpretable guidance for iterative redesign. By positioning agents as both designers and judges, our framework shifts interface design toward agent-native efficiency and reliability. Our work takes a step toward shifting agents from passive use toward active participation in digital environments. Our code and dataset are available at https://github.com/showlab/AUI.