Imagen de Portada

GUIDE: A Benchmark for Understanding and Assisting Users in Open-Ended GUI Tasks

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yang, Saelyne, Yu, Jaesang, Peng, Yi-Hao, Lin, Kevin Qinghong, Cho, Jae Won, Song, Yale, Kim, Juho
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence Human-Computer Interaction
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

VideoMix: Aggregating How-To Videos for Task-Oriented Learning
por: Yang, Saelyne, et al.
Publicado: (2025)

Contexty: Capturing and Organizing In-situ Thoughts for Context-Aware AI Support
por: Kim, Yoonsu, et al.
Publicado: (2026)

IdeaBlocks: Expressing and Reusing Divergent Intents for Graphic Design Exploration using Generative AI
por: Choi, DaEun, et al.
Publicado: (2025)

ExpressEdit: Video Editing with Natural Language and Sketching
por: Tilekbay, Bekzat, et al.
Publicado: (2024)

How Neurotypical and Autistic Children Interact Nonverbally with Anthropomorphic Agents in Open-Ended Tasks
por: Zhang, Chuxuan, et al.
Publicado: (2026)

"I Can't Keep Up": Accessibility Barriers in Video-Based Learning for Individuals with Borderline Intellectual Functioning
por: Chu, Hyehyun, et al.
Publicado: (2026)

ShowUI-$π$: Flow-based Generative Models as GUI Dexterous Hands
por: Hu, Siyuan, et al.
Publicado: (2025)

Predicting and Understanding Turn-Taking Behavior in Open-Ended Group Activities in Virtual Reality
por: Wang, Portia, et al.
Publicado: (2024)

AQuA: Automated Question-Answering in Software Tutorial Videos with Visual Anchors
por: Yang, Saelyne, et al.
Publicado: (2024)

GUIDE: Graphical User Interface Data for Execution
por: Chawla, Rajat, et al.
Publicado: (2024)

Understanding Users' Dissatisfaction with ChatGPT Responses: Types, Resolving Tactics, and the Effect of Knowledge Level
por: Kim, Yoonsu, et al.
Publicado: (2023)

Does Difficulty even Matter? Investigating Difficulty Adjustment and Practice Behavior in an Open-Ended Learning Task
por: Schütt, Anan, et al.
Publicado: (2023)

CRAFT-GUI: Curriculum-Reinforced Agent For GUI Tasks
por: Nong, Songqin, et al.
Publicado: (2025)

Cheap and Easy Open-Ended Text Input for Interactive Emergent Narrative
por: Kreminski, Max
Publicado: (2024)

Social Media Should Feel Like Minecraft, Not Instagram: Youth Visions for Meaningful Social Connections through Fictional Inquiry
por: Kim, JaeWon, et al.
Publicado: (2025)

Problem Space Attunement in Youth Social Media Design
por: Kim, JaeWon
Publicado: (2026)

Understanding the Challenges of OpenSCAD Users for 3D Printing
por: Gonzalez, J. Felipe, et al.
Publicado: (2024)

LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark
por: Liu, Guangyi, et al.
Publicado: (2025)

From Consumption to Collaboration: Measuring Interaction Patterns to Augment Human Cognition in Open-Ended Tasks
por: Holstein, Joshua, et al.
Publicado: (2025)

Establishing Heuristics for Improving the Usability of GUI Machine Learning Tools for Novice Users
por: Yamani, Asma, et al.
Publicado: (2024)

GLOSS: Group of LLMs for Open-Ended Sensemaking of Passive Sensing Data for Health and Wellbeing
por: Choube, Akshat, et al.
Publicado: (2025)

OmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone Environments
por: Henry, Felix, et al.
Publicado: (2026)

SlideItRight: Using AI to Find Relevant Slides and Provide Feedback for Open-Ended Questions
por: Zhao, Chloe Qianhui, et al.
Publicado: (2025)

Fast Multi-Party Open-Ended Conversation with a Social Robot
por: Abbo, Giulio Antonio, et al.
Publicado: (2025)

Improving Data Quality via Pre-Task Participant Screening in Crowdsourced GUI Experiments
por: Miyama, Takaya, et al.
Publicado: (2026)

VenusBench-Mobile: A Challenging and User-Centric Benchmark for Mobile GUI Agents with Capability Diagnostics
por: Gong, Yichen, et al.
Publicado: (2026)

Metaphors as Scaffolds: Spatial, Embodied, Fantastical, and Relational Framings for Youth Usable Privacy Design
por: Kim, JaeWon, et al.
Publicado: (2026)

Privacy as Social Norm: Systematically Reducing Dysfunctional Privacy Concerns on Social Media
por: Kim, JaeWon, et al.
Publicado: (2024)

Beyond Tools: Understanding How Heavy Users Integrate LLMs into Everyday Tasks and Decision-Making
por: Kim, Eunhye, et al.
Publicado: (2025)

Trust-Enabled Privacy: Social Media Designs to Support Adolescent User Boundary Regulation
por: Kim, JaeWon, et al.
Publicado: (2025)

"Are we writing an advice column for Spock here?" Understanding Stereotypes in AI Advice for Autistic Users
por: Wohn, Caleb, et al.
Publicado: (2026)

GraphPilot: GUI Task Automation with One-Step LLM Reasoning Powered by Knowledge Graph
por: Yu, Mingxian, et al.
Publicado: (2026)

Code2World: A GUI World Model via Renderable Code Generation
por: Zheng, Yuhao, et al.
Publicado: (2026)

Spotting Out-of-Character Behavior: Atomic-Level Evaluation of Persona Fidelity in Open-Ended Generation
por: Shin, Jisu, et al.
Publicado: (2025)

TaskSense: Cognitive Chain Modeling and Difficulty Estimation for GUI Tasks
por: Yin, Yiwen, et al.
Publicado: (2025)

A User-Centered Teleoperation GUI for Automated Vehicles: Identifying and Evaluating Information Requirements for Remote Driving and Assistance
por: Wolf, Maria-Magdalena, et al.
Publicado: (2025)

Authorship Drift: How Self-Efficacy and Trust Evolve During LLM-Assisted Writing
por: Park, Yeon Su, et al.
Publicado: (2026)

DiscoverLLM: From Executing Intents to Discovering Them
por: Kim, Tae Soo, et al.
Publicado: (2026)

"Having Lunch Now": Understanding How Users Engage with a Proactive Agent for Daily Planning and Self-Reflection
por: Abbas, Adnan, et al.
Publicado: (2025)

"Do I Trust the AI?" Towards Trustworthy AI-Assisted Diagnosis: Understanding User Perception in LLM-Supported Reasoning
por: Xu, Yuansong, et al.
Publicado: (2026)