Awesome GUI Agent

A curated list of papers, projects, and resources for multi-modal Graphical User Interface (GUI) agents.

Build a digital assistant on your screen. Generated by DALL-E-3.

WELCOME CONTRIBUTE!

🔥 This project is actively maintained, and we welcome your contributions. If you have any suggestions, such as missing papers or information, please feel free to open an issue or submit a pull request.

🤖 Try our Awesome-Paper-Agent. Just provide an arXiv URL link, and it will automatically return formatted information, like this:

User:
https://arxiv.org/abs/2312.13108

GPT:
+ [AssistGUI: Task-Oriented Desktop Graphical User Interface Automation](https://arxiv.org/abs/2312.13108) (Dec. 2023)

  [![Star](https://img.shields.io/github/stars/showlab/assistgui.svg?style=social&label=Star)](https://github.com/showlab/assistgui)
  [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.13108)
  [![Website](https://img.shields.io/badge/Website-9cf)](https://showlab.github.io/assistgui/)

So then you can easily copy and use this information in your pull requests.

⭐ If you find this repository useful, please give it a star.

Datasets / Benchmarks

• World of Bits: An Open-Domain Platform for Web-Based Agents (Aug. 2017, ICML 2017)

  

• A Unified Solution for Structured Web Data Extraction (Jul. 2011, SIGIR 2011)

  

• Rico: A Mobile App Dataset for Building Data-Driven Design Applications (Oct. 2017)

  

• Reinforcement Learning on Web Interfaces using Workflow-Guided Exploration (Feb. 2018, ICLR 2018)

  

• Mapping Natural Language Instructions to Mobile UI Action Sequences (May. 2020, ACL 2020)

  

• WebSRC: A Dataset for Web-Based Structural Reading Comprehension (Jan. 2021, EMNLP 2021)

  

• AndroidEnv: A Reinforcement Learning Platform for Android (May. 2021)

  

• A Dataset for Interactive Vision-Language Navigation with Unknown Command Feasibility (Feb. 2022)

  

• META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI (May. 2022)

  

• WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents (Jul. 2022)

  

• Language Models can Solve Computer Tasks (Mar. 2023)

  

• Mobile-Env: Building Qualified Evaluation Benchmarks for LLM-GUI Interaction (May. 2023)

  

• Mind2Web: Towards a Generalist Agent for the Web (Jun. 2023)

  

• Android in the Wild: A Large-Scale Dataset for Android Device Control (Jul. 2023)

  

• WebArena: A Realistic Web Environment for Building Autonomous Agents (Jul. 2023)

  

• Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language Models (Nov. 2023)

  

• AssistGUI: Task-Oriented Desktop Graphical User Interface Automation (Dec. 2023, CVPR 2024)

  

• VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks (Jan. 2024, ACL 2024)

  

• OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web (Feb. 2024)

  

• WebLINX: Real-World Website Navigation with Multi-Turn Dialogue (Feb. 2024)

  

• On the Multi-turn Instruction Following for Conversational Web Agents (Feb. 2024)

  

• AgentStudio: A Toolkit for Building General Virtual Agents (Mar. 2024)

  

• OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments (Apr. 2024)

  

• Benchmarking Mobile Device Control Agents across Diverse Configurations (Apr. 2024, ICLR 2024)

  

• MMInA: Benchmarking Multihop Multimodal Internet Agents (Apr. 2024)

  

• Autonomous Evaluation and Refinement of Digital Agents (Apr. 2024)

  

• LlamaTouch: A Faithful and Scalable Testbed for Mobile UI Automation Task Evaluation (Apr. 2024)

  

• VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding? (Apr. 2024)

  

• GUICourse: From General Vision Language Models to Versatile GUI Agents (Jun. 2024)

  

• GUI-WORLD: A Dataset for GUI-oriented Multimodal LLM-based Agents (Jun. 2024)

  

• GUI Odyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices (Jun. 2024)

  

• VideoGUI: A Benchmark for GUI Automation from Instructional Videos (Jun. 2024)

  

• Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding (Jun. 2024)

  

• MobileAgentBench: An Efficient and User-Friendly Benchmark for Mobile LLM Agents (Jun. 2024)

  

• AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents (Jun. 2024)

  

• Practical, Automated Scenario-based Mobile App Testing (Jun. 2024)

  

• WebCanvas: Benchmarking Web Agents in Online Environments (Jun. 2024)

  

• CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents (Jul. 2024)

  

• WebVLN: Vision-and-Language Navigation on Websites (AAAI 2024)

  

• Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows? (Jul. 2024)

  

Models / Agents

• Grounding Open-Domain Instructions to Automate Web Support Tasks (Mar. 2021)

  

• Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning (Aug. 2021)

  

• A Data-Driven Approach for Learning to Control Computers (Feb. 2022)

  

• Augmenting Autotelic Agents with Large Language Models (May. 2023)

  

• Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control (Jun. 2023, ICLR 2024)

  

• A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis (Jul. 2023, ICLR 2024)

  

• LASER: LLM Agent with State-Space Exploration for Web Navigation (Sep. 2023)

  

• CogAgent: A Visual Language Model for GUI Agents (Dec. 2023, CVPR 2024)

  

• WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models

  

• OS-Copilot: Towards Generalist Computer Agents with Self-Improvement (Feb. 2024)

  

• UFO: A UI-Focused Agent for Windows OS Interaction (Feb. 2024)

  

• Comprehensive Cognitive LLM Agent for Smartphone GUI Automation (Feb. 2024)

  

• Improving Language Understanding from Screenshots (Feb. 2024)

  

• AutoWebGLM: Bootstrap And Reinforce A Large Language Model-based Web Navigating Agent (Apr. 2024, KDD 2024)

  

• SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models (May. 2023, NeurIPS 2023)

  

• You Only Look at Screens: Multimodal Chain-of-Action Agents (Sep. 2023)

  

• Reinforced UI Instruction Grounding: Towards a Generic UI Task Automation API (Oct. 2023)

  

• OpenAgents: AN OPEN PLATFORM FOR LANGUAGE AGENTS IN THE WILD (Oct. 2023)

  

• GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation (Nov. 2023)

  

• AppAgent: Multimodal Agents as Smartphone Users (Dec. 2023)

  

• SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents (Jan. 2024, ACL 2024)

  

• GPT-4V(ision) is a Generalist Web Agent, if Grounded (Jan. 2024, ICML 2024)

  

• Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception (Jan. 2024)

  

• Dual-View Visual Contextualization for Web Navigation (Feb. 2024, CVPR 2024)

  

• DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning (Jun. 2024)

  

• Visual Grounding for User Interfaces (NAACL 2024)

  

• ScreenAgent: A Computer Control Agent Driven by Visual Language Large Model (Feb. 2024)

  

• ScreenAI: A Vision-Language Model for UI and Infographics Understanding (Feb. 2024)

  

• Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs (Apr. 2024)

  

• Octopus: On-device language model for function calling of software APIs (Apr., 2024)

  

• Octopus v2: On-device language model for super agent (Apr., 2024)

  

• Octopus v3: Technical Report for On-device Sub-billion Multimodal AI Agent (Apr., 2024)

  

• Octopus v4: Graph of language models (Apr., 2024)

  

• AutoWebGLM: Bootstrap and Reinforce a Large Language Model-based Web Navigating Agent (Apr. 2024)

  

• Search Beyond Queries: Training Smaller Language Models for Web Interactions via Reinforcement Learning (Apr. 2024)

  

• Enhancing Mobile "How-to" Queries with Automated Search Results Verification and Reranking (Apr. 2024, SIGIR 2024)

  

• AutoDroid: LLM-powered Task Automation in Android

  

• Towards General Computer Control: A Multimodal Agent for Red Dead Redemption II as a Case Study (Mar. 2024)

  

• Android in the Zoo: Chain-of-Action-Thought for GUI Agents (Mar. 2024)

  

• GUI Action Narrator: Where and When Did That Action Take Place? (Jun. 2024)

  

• Identifying User Goals from UI Trajectories (Jun. 2024)

  

• VGA: Vision GUI Assistant -- Minimizing Hallucinations through Image-Centric Fine-Tuning (Jun. 2024)

  

• Octo-planner: On-device Language Model for Planner-Action Agents (Jun. 2024)

  

• E-ANT: A Large-Scale Dataset for Efficient Automatic GUI NavigaTion (Jun. 2024)

  

• Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration (Jun. 2024)

  

• MobileFlow: A Multimodal LLM For Mobile GUI Agent (Jul. 2024)

  

• Vision-driven Automated Mobile GUI Testing via Multimodal Large Language Model (Jul. 2024)

  

• Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence (Jul. 2024)

  

• MobileExperts: A Dynamic Tool-Enabled Agent Team in Mobile Devices (Jul. 2024)

  

• AUITestAgent: Automatic Requirements Oriented GUI Function Testing (Jul. 2024)

  

• Agent-E: From Autonomous Web Navigation to Foundational Design Principles in Agentic Systems (Jul. 2024)

  

• OmniParser for Pure Vision Based GUI Agent (Aug. 2024)

  

Projects

• PyAutoGUI

  

• GPT-4V-Act: AI agent using GPT-4V(ision) for web UI interaction

  

• gpt-computer-assistant

  

• Mobile-Agent: The Powerful Mobile Device Operation Assistant Family

  

• OpenUI

  

• ACT-1

  

• NatBot

  

• Multion

  

• Auto-GPT

  

• WebLlama

  

• LaVague: Large Action Model Framework to Develop AI Web Agents

• AGI Computer Control

Acknowledgements

This template is provided by Awesome-Video-Diffusion and Awesome-MLLM-Hallucination.