Morae: Proactively Pausing UI Agents for User Choices
Yi-Hao Peng, Dingzeyu Li, Jeffrey P. Bigham, Amy Pavel
2025年份
4被引次数
10顶会引用
摘要
Figure 1: Morae is an accessible user interface agent that proactively pauses automation at key decision points for blind and low-vision users to make choices. For example, when asked to "buy the cheapest sweetened sparkling water", existing agents would automatically choose a product even if multiple items have identical prices. Instead, Morae pauses automation and presents relevant product differences (e.g., flavors, ratings) and allows users to choose based on their preferences. By proactively detecting and pausing when user input is necessary, Morae allow users to actively express preferences during UI automation.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper10
- Cocoa: Co-Planning and Co-Execution with AI AgentsK. J. Kevin Feng, Kevin Pu, Matt Latzke, Tal August 等CHI 2026 · 被引用 6 次
- GUIDE: A Benchmark for Understanding and Assisting Users in Open-Ended GUI TasksSaelyne Yang, Jaesang Yu, Yi-Hao Peng, Kevin Qinghong Lin 等CVPR 2026 · 被引用 5 次
- Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human OversightJingyu Tang, Chaoran Chen, Jiawen Li, Zhiping Zhang 等CHI 2026 · 被引用 4 次
- Code with Me or for Me? How Increasing AI Automation Transforms Developer WorkflowsValerie Chen, Ameet Talwalkar, Robert Brennan, Graham NeubigCHI 2026 · 被引用 2 次
- A11y-CUA Dataset: Characterizing the Accessibility Gap in Computer Use AgentsAnanya Gubbi Mohanbabu, Rosiana Natalie, Brandon Kim, Anhong Guo 等CHI 2026 · 被引用 1 次
它引用的顶会 Paper27
- WebArena: A Realistic Web Environment for Building Autonomous AgentsShuyan Zhou, Frank F. Xu, Hao Zhu, Xuhui Zhou 等ICLR 2024 · 被引用 1,197 次
- Language Models can Solve Computer TasksGeunwoo Kim, Pierre Baldi, Stephen McAleerNeurIPS 2023 · 被引用 539 次
- TEACh: Task-Driven Embodied Agents That ChatAishwarya Padmakumar, Jesse Thomason, Ayush Shrivastava, Patrick Lange 等AAAI 2022 · 被引用 251 次
- DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement LearningHao Bai, Yifei Zhou, Jiayi Pan, Mert Cemri 等NeurIPS 2024 · 被引用 239 次
- Enabling Conversational Interaction with Mobile UI using Large Language ModelsBryan Wang, Gang Li, Yang LiCHI 2023 · 被引用 149 次
相关 Paper
- Toward Independent Online Shopping of the Visually Impaired Through Voice-based Computer-Using AgentSubin Shin, Jeesun Oh, Suhyun Kim, Seoyeon Eom 等CHI 2026 · 被引用 1 次
- Automating UI Optimization through Multi-Agentic ReasoningZhipeng Li, Christoph Gebhardt, Yi-Chi Liao, Christian HolzCHI 2026 · 被引用 1 次
- Programmers Who Use Screen Readers in the Vibe Coding Era: Adaptation, Empowerment, and New Accessibility LandscapeNan Chen, Luna K. Qiu, Arran Zeyu Wang, Zilong Wang 等CHI 2026 · 被引用 2 次
- Defining Patterns for a Conversational WebEmanuele Pucci, Isabella Possaghi, Claudia Maria Cutrupi, Marcos Báez 等CHI 2023 · 被引用 29 次
- When Refreshable Tactile Displays Meet Conversational Agents: Investigating Accessible Data Presentation and Analysis with Touch and SpeechSamuel Reinders, Matthew Butler, Ingrid Zukerman, Bongshin Lee 等IEEE VIS 2024 · 被引用 24 次
