{"total":18,"rows":[{"id":"2411.18279","title":"Large Language Model-Brained GUI Agents: A Survey","created":"2024-11-27","cited_by_count":162,"area":"agents"},{"id":"2505.13227","title":"Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis","created":"2025-05-19","cited_by_count":139,"area":"agents"},{"id":"2412.10471","title":"VCA: Video Curious Agent for Long Video Understanding","created":"2024-12-12","cited_by_count":56,"area":"agents"},{"id":"2412.15606","title":"Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage","created":"2024-12-20","cited_by_count":51,"area":"agents"},{"id":"2504.19838","title":"LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects","created":"2025-04-28","cited_by_count":32,"area":"agents"},{"id":"2508.21767","title":"UItron: Foundational GUI Agent with Advanced Perception and Planning","created":"2025-08-29","cited_by_count":22,"area":"agents"},{"id":"2508.03700","title":"MagicGUI: A Foundational Mobile GUI Agent with Scalable Data Pipeline and Reinforcement Fine-tuning","created":"2025-07-19","cited_by_count":19,"area":"agents"},{"id":"2503.03196","title":"SpiritSight Agent: Advanced GUI Agent with One Look","created":"2025-03-05","cited_by_count":18,"area":"agents"},{"id":"2505.00416","title":"ScaleTrack: Scaling and back-tracking Automated GUI Agents","created":"2025-05-01","cited_by_count":16,"area":"agents"},{"id":"2505.18229","title":"BEDI: A Comprehensive Benchmark for Evaluating Embodied Agents on UAVs","created":"2025-05-23","cited_by_count":10,"area":"agents"},{"id":"2508.19493","title":"Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents","created":"2025-08-27","cited_by_count":8,"area":"agents"},{"id":"2509.17191","title":"VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery","created":"2025-09-21","cited_by_count":6,"area":"agents"},{"id":"2512.11611","title":"Using GUI Agent for Electronic Design Automation","created":"2025-12-12","cited_by_count":5,"area":"agents"},{"id":"2510.08789","title":"Q-Router: Agentic Video Quality Assessment with Expert Model Routing and Artifact Localization","created":"2025-10-09","cited_by_count":2,"area":"agents"},{"id":"2511.18192","title":"ARIAL: An Agentic Framework for Document VQA with Precise Answer Localization","created":"2025-11-22","cited_by_count":2,"area":"agents"},{"id":"2602.00454","title":"Cross-Modal Memory Compression for Efficient Multi-Agent Debate","created":"2026-01-31","cited_by_count":2,"area":"agents"},{"id":"2603.12597","title":"Feynman: Knowledge-Infused Diagramming Agent for Scalable Visual Designs","created":"2026-03-13","cited_by_count":1,"area":"agents"},{"id":"2604.23941","title":"GoClick: Lightweight Element Grounding Model for Autonomous GUI Interaction","created":"2026-04-27","cited_by_count":0,"area":"agents"}],"next_cursor":null}