{"total":13,"rows":[{"id":"2508.09123","title":"OpenCUA: Open Foundations for Computer-Use Agents","created":"2025-08-12","cited_by_count":160,"area":"mllm"},{"id":"2605.27365","title":"LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding","created":"2026-05-26","cited_by_count":28,"area":"mllm"},{"id":"2508.05731","title":"InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization","created":"2025-08-07","cited_by_count":27,"area":"mllm"},{"id":"2510.10991","title":"A Survey on Agentic Multimodal Large Language Models","created":"2025-10-13","cited_by_count":23,"area":"mllm"},{"id":"2510.04039","title":"\\textsc{GUI-Spotlight}: Adaptive Iterative Focus Refinement for Enhanced GUI Visual Grounding","created":"2025-10-05","cited_by_count":10,"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":"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":"2603.15039","title":"GUI-CEval: A Hierarchical and Comprehensive Chinese Benchmark for Mobile GUI Agents","created":"2026-03-16","cited_by_count":3,"area":"mllm"},{"id":"2604.07413","title":"FORGE: Fine-grained Multimodal Evaluation for Manufacturing Scenarios","created":"2026-04-08","cited_by_count":2,"area":"mllm"},{"id":"2606.25760","title":"Uncertainty Quantification for Computer-Use Agents: A Benchmark across Vision-Language Models and GUI Grounding Datasets","created":"2026-06-24","cited_by_count":2,"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":"2610.05185","title":"Recurrent Latent Visual Search for GUI Grounding","created":"2026-10-04","cited_by_count":0,"area":"mllm"}],"next_cursor":null}