Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning

Screen2Words introduces a mobile UI summarization task with over 112k human-written summaries covering 22,417 Android screens. It studies how to generate concise screen-level descriptions from the multimodal content of a UI rather than only captioning individual elements.

• PSPA-Bench: A Personalized Benchmark for Smartphone GUI Agent
  March 31, 2026 · arXiv
• SecAgent: Efficient Mobile GUI Agent with Semantic Context
  March 9, 2026 · arXiv
• Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization
  February 24, 2026 · arXiv
• AmbiBench: Benchmarking Mobile GUI Agents Beyond One-Shot Instructions in the Wild
  February 12, 2026 · arXiv
• MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments
  February 3, 2026 · arXiv
• SwipeGen: Bridging the Execution Gap in GUI Agents via Human-like Swipe Synthesis
  January 26, 2026 · arXiv
• SMAN-Bench: A Cross-System Benchmark for Mobile Agents under Single- and Multi-path, Ambiguous, and Noisy Tasks
  January 26, 2026 · ICLR 2026 (Poster)
• MobileWorldBench: Towards Semantic World Modeling For Mobile Agents
  December 16, 2025 · arXiv
• NaturalGAIA: Pushing the Frontiers of GUI Agents with a Challenging Benchmark and High-Quality Trajectory Dataset
  August 2, 2025 · arXiv
• FingerTip 20K: A Benchmark for Proactive and Personalized Mobile LLM Agents
  June 9, 2025 · ICLR 2026 (Poster)
• LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark
  April 18, 2025 · arXiv
• AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents
  October 31, 2024 · ACL 2025
• GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding
  June 16, 2024 · ICLR 2025 (Poster)
• LlamaTouch: A Faithful and Scalable Testbed for Mobile UI Task Automation
  April 12, 2024 · UIST 2024
• Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs
  April 8, 2024 · ECCV 2024 (Poster)
• SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents
  January 17, 2024 · ACL 2024
• GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation
  November 13, 2023 · arXiv
• Android in the Wild: A Large-Scale Dataset for Android Device Control
  July 19, 2023 · NeurIPS 2023 Datasets and Benchmarks Track
• A Dataset for Interactive Vision-Language Navigation with Unknown Command Feasibility
  February 4, 2022 · ECCV 2022
• Widget Captioning: Generating Natural Language Description for Mobile User Interface Elements
  November 30, 2020 · EMNLP 2020
• Mapping Natural Language Instructions to Mobile UI Action Sequences
  July 31, 2020 · ACL 2020
• WebForge: Breaking the Realism-Reproducibility-Scalability Trilemma in Browser Agent Benchmark
  April 13, 2026 · arXiv
• Gym-Anything: Turn any Software into an Agent Environment
  April 7, 2026 · arXiv
• WebArena-Infinity: Generating Browser Environments with Verifiable Tasks at Scale
  March 2026 · Blog Post