{"total":25,"rows":[{"id":"2410.05243","title":"Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents","created":"2024-10-07","cited_by_count":382,"area":"mllm"},{"id":"2410.23218","title":"OS-ATLAS: A Foundation Action Model for Generalist GUI Agents","created":"2024-10-30","cited_by_count":378,"area":"mllm"},{"id":"2509.15221","title":"ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data","created":"2025-09-18","cited_by_count":60,"area":"mllm"},{"id":"2506.08012","title":"GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior","created":"2025-06-09","cited_by_count":23,"area":"mllm"},{"id":"2504.11257","title":"UI-E2I-Synth: Advancing GUI Grounding with Large-Scale Instruction Synthesis","created":"2025-04-15","cited_by_count":20,"area":"mllm"},{"id":"2506.10387","title":"Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills","created":"2025-06-12","cited_by_count":19,"area":"mllm"},{"id":"2509.24183","title":"Retrieval-augmented GUI Agents with Generative Guidelines","created":"2025-09-29","cited_by_count":15,"area":"mllm"},{"id":"2505.12632","title":"Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents","created":"2025-05-19","cited_by_count":14,"area":"mllm"},{"id":"2503.00743","title":"Quality-Driven Curation of Remote Sensing Vision-Language Data via Learned Scoring Models","created":"2025-03-02","cited_by_count":11,"area":"mllm"},{"id":"2601.03928","title":"FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection","created":"2026-01-07","cited_by_count":10,"area":"mllm"},{"id":"2506.15425","title":"Understanding GUI Agent Localization Biases through Logit Sharpness","created":"2025-06-18","cited_by_count":8,"area":"mllm"},{"id":"2605.14747","title":"Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining","created":"2026-05-14","cited_by_count":7,"area":"mllm"},{"id":"2509.03536","title":"PG-Agent: An Agent Powered by Page Graph","created":"2025-08-27","cited_by_count":6,"area":"mllm"},{"id":"2603.14448","title":"Zoom to Essence: Trainless GUI Grounding by Inferring upon Interface Elements","created":"2026-03-15","cited_by_count":5,"area":"mllm"},{"id":"2604.27974","title":"FineState-Bench: Benchmarking State-Conditioned Grounding for Fine-grained GUI State Setting","created":"2026-04-30","cited_by_count":5,"area":"mllm"},{"id":"2605.15542","title":"DRS-GUI: Dynamic Region Search for Training-Free GUI Grounding","created":"2026-05-15","cited_by_count":5,"area":"mllm"},{"id":"2602.02468","title":"Avenir-Web: Human-Experience-Imitating Multimodal Web Agents with Mixture of Grounding Experts","created":"2026-02-02","cited_by_count":4,"area":"mllm"},{"id":"2603.26266","title":"GUIDE: Resolving Domain Bias in GUI Agents through Real-Time Web Video Retrieval and Plug-and-Play Annotation","created":"2026-03-27","cited_by_count":4,"area":"mllm"},{"id":"2510.22102","title":"Mitigating Coordinate Prediction Bias from Positional Encoding Failures","created":"2025-10-25","cited_by_count":2,"area":"mllm"},{"id":"2505.05895","title":"Leveraging Vision-Language Models for Visual Grounding and Analysis of Automotive UI","created":"2025-05-09","cited_by_count":1,"area":"mllm"},{"id":"2604.09442","title":"UIPress: Bringing Optical Token Compression to UI-to-Code Generation","created":"2026-04-10","cited_by_count":1,"area":"mllm"},{"id":"2605.19260","title":"AQuaUI: Visual Token Reduction for GUI Agents with Adaptive Quadtrees","created":"2026-05-19","cited_by_count":1,"area":"mllm"},{"id":"2510.03612","title":"Cross-Modal Content Optimization for Steering Web Agent Preferences","created":"2025-10-04","cited_by_count":0,"area":"mllm"},{"id":"2608.09654","title":"Hallucination-Free GUI Grounding via Regression-Free Layout-Aware Matching","created":"2026-08-10","cited_by_count":0,"area":"mllm"},{"id":"2610.20107","title":"Why Generate a Click? Plug-in Decision Heads for Web Agents","created":"2026-10-14","cited_by_count":0,"area":"mllm"}],"next_cursor":null}