{"total":38,"rows":[{"id":"2411.18279","title":"Large Language Model-Brained GUI Agents: A Survey","created":"2024-11-27","cited_by_count":162,"area":"agents"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2407.17490","title":"AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents","created":"2024-07-03","cited_by_count":113,"area":"agents"},{"id":"2501.02341","title":"UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility","created":"2025-01-04","cited_by_count":49,"area":"agents"},{"id":"2605.15187","title":"Articraft: An Agentic System for Scalable Articulated 3D Asset Generation","created":"2026-05-14","cited_by_count":30,"area":"agents"},{"id":"2503.23452","title":"VideoGen-Eval: Agent-based System for Video Generation Evaluation","created":"2025-03-30","cited_by_count":23,"area":"agents"},{"id":"2403.09027","title":"VisionGPT: Vision-Language Understanding Agent Using Generalized Multimodal Framework","created":"2024-03-14","cited_by_count":20,"area":"agents"},{"id":"2602.22839","title":"DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation","created":"2026-02-26","cited_by_count":18,"area":"agents"},{"id":"2505.07634","title":"Neural Brain: A Neuroscience-inspired Framework for Embodied Agents","created":"2025-05-12","cited_by_count":10,"area":"agents"},{"id":"2508.17198","title":"From reactive to cognitive: brain-inspired spatial intelligence for embodied agents","created":"2025-08-24","cited_by_count":7,"area":"agents"},{"id":"2603.17343","title":"EvoGuard: An Extensible Agentic RL-based Framework for Practical and Evolving AI-Generated Image Detection","created":"2026-03-18","cited_by_count":6,"area":"agents"},{"id":"2504.19818","title":"PhenoAssistant: A Conversational Multi-Agent AI System for Automated Plant Phenotyping","created":"2025-04-28","cited_by_count":4,"area":"agents"},{"id":"2505.22311","title":"From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communications","created":"2025-05-28","cited_by_count":2,"area":"agents"},{"id":"2603.05884","title":"Computational Pathology in the Era of Emerging Foundation and Agentic AI -- International Expert Perspectives on Clinical Integration and Translational Readiness","created":"2026-03-06","cited_by_count":2,"area":"agents"},{"id":"2603.14052","title":"A Multi-Agent Perception-Action Alliance for Efficient Long Video Reasoning","created":"2026-03-14","cited_by_count":2,"area":"agents"},{"id":"2601.22571","title":"PerfGuard: A Performance-Aware Agent for Visual Content Generation","created":"2026-01-30","cited_by_count":1,"area":"agents"},{"id":"2603.15916","title":"Auto Researching, not hyperparameter tuning: Convergence Analysis of 10,000 Experiments","created":"2026-03-16","cited_by_count":1,"area":"agents"},{"id":"2608.03298","title":"SeaSlides: Semantic Abstraction Layer for Agentic Slide Generation","created":"2026-08-04","cited_by_count":1,"area":"agents"},{"id":"2602.17030","title":"Patch-Based Spatial Authorship Attribution in Human-Robot Collaborative Paintings","created":"2026-02-19","cited_by_count":0,"area":"agents"},{"id":"2603.05873","title":"Shifting Adaptation from Weight Space to Memory Space: A Memory-Augmented Agent for Medical Image Segmentation","created":"2026-03-06","cited_by_count":0,"area":"agents"},{"id":"2603.25420","title":"VideoWeaver: Multimodal Multi-View Video-to-Video Transfer for Embodied Agents","created":"2026-03-26","cited_by_count":0,"area":"agents"},{"id":"2604.13236","title":"SemiFA: An Agentic Multi-Modal Framework for Autonomous Semiconductor Failure Analysis Report Generation","created":"2026-04-14","cited_by_count":0,"area":"agents"},{"id":"2605.10397","title":"AnomalyClaw: A Universal Visual Anomaly Detection Agent via Tool-Grounded Refutation","created":"2026-05-11","cited_by_count":0,"area":"agents"},{"id":"2605.18727","title":"DexHoldem: Playing Texas Hold'em with Dexterous Embodied System","created":"2026-05-18","cited_by_count":0,"area":"agents"},{"id":"2605.28683","title":"VeriTrip: A Verifiable Benchmark for Travel Planning Agents over Unstructured Web Corpora","created":"2026-05-27","cited_by_count":0,"area":"agents"},{"id":"2606.13878","title":"AnyGoal: Vision-Language Guided Multi-Agent Exploration for Training-Free Lifelong Navigation","created":"2026-06-11","cited_by_count":0,"area":"agents"},{"id":"2606.30632","title":"GROW$^2$: Grounding Which and Where for Robot Tool Use","created":"2026-06-29","cited_by_count":0,"area":"agents"},{"id":"2607.18080","title":"Sparse Evidence Can Suffice: Agentic Evidence Seeking for Multimodal Video Misinformation Detection","created":"2026-07-20","cited_by_count":0,"area":"agents"},{"id":"2608.00847","title":"Models as Tools: An Agentic Coordination Framework for Unified Multimodal Visual Tracking","created":"2026-08-01","cited_by_count":0,"area":"agents"},{"id":"2609.04802","title":"Linguistic Trajectory Encoding for Efficient Long-Horizon Spatial Memory in Embodied Agents","created":"2026-09-04","cited_by_count":0,"area":"agents"},{"id":"2609.06208","title":"From Gaze to Meaning: A Training-Free AI Agent for Unified Grounding and Explanation","created":"2026-09-05","cited_by_count":0,"area":"agents"},{"id":"2609.13240","title":"ArtSociety: Multi-Agent Multimodal Collaboration for Art Emotion Understanding","created":"2026-09-03","cited_by_count":0,"area":"agents"},{"id":"2609.13348","title":"ViFA-Council: Multi-Agent LLM Deliberation for Vietnamese Folk Art Generation","created":"2026-07-11","cited_by_count":0,"area":"agents"},{"id":"2609.20330","title":"RoboFind: Multi-Agent Personalized Object Search for People Who Are Blind or Have Low Vision","created":"2026-09-17","cited_by_count":0,"area":"agents"},{"id":"2609.33627","title":"StoryEngine: A State-Grounded Agentic Framework for Video Storytelling","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2610.12126","title":"SuperNav: An Agentic Navigation System for Any Task in Any Scene","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.12403","title":"ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.15582","title":"Inverse Garment Design with Visual Agents","created":"2026-10-11","cited_by_count":0,"area":"agents"}],"next_cursor":null}