{"total":91,"rows":[{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439,"area":"agents"},{"id":"2311.12871","title":"An Embodied Generalist Agent in 3D World","created":"2023-11-18","cited_by_count":365,"area":"agents"},{"id":"2403.10517","title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent","created":"2024-03-15","cited_by_count":332,"area":"agents"},{"id":"2305.18752","title":"GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction","created":"2023-05-30","cited_by_count":248,"area":"agents"},{"id":"2309.11436","title":"You Only Look at Screens: Multimodal Chain-of-Action Agents","created":"2023-09-20","cited_by_count":185,"area":"agents"},{"id":"2401.03568","title":"Agent AI: Surveying the Horizons of Multimodal Interaction","created":"2024-01-07","cited_by_count":170,"area":"agents"},{"id":"2505.10468","title":"AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges","created":"2025-05-15","cited_by_count":169,"area":"agents"},{"id":"2407.01476","title":"Tree Search for Language Model Agents","created":"2024-07-01","cited_by_count":151,"area":"agents"},{"id":"2511.05271","title":"DeepEyesV2: Toward Agentic Multimodal Model","created":"2025-11-07","cited_by_count":125,"area":"agents"},{"id":"2503.09780","title":"AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents","created":"2025-03-12","cited_by_count":82,"area":"agents"},{"id":"2505.02836","title":"Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation","created":"2025-05-05","cited_by_count":67,"area":"agents"},{"id":"2311.16714","title":"Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld","created":"2023-11-28","cited_by_count":65,"area":"agents"},{"id":"2401.08392","title":"DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)","created":"2024-01-16","cited_by_count":58,"area":"agents"},{"id":"2404.09992","title":"MMInA: Benchmarking Multihop Multimodal Internet Agents","created":"2024-04-15","cited_by_count":55,"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":"2310.13255","title":"Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worlds","created":"2023-10-20","cited_by_count":45,"area":"agents"},{"id":"2511.19663","title":"Fara-7B: An Efficient Agentic Model for Computer Use","created":"2025-11-24","cited_by_count":35,"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":"2403.11835","title":"Agent3D-Zero: An Agent for Zero-shot 3D Understanding","created":"2024-03-18","cited_by_count":29,"area":"agents"},{"id":"2512.05774","title":"Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding","created":"2025-12-05","cited_by_count":29,"area":"agents"},{"id":"2412.10402","title":"TANGO: Training-free Embodied AI Agents for Open-world Tasks","created":"2024-12-05","cited_by_count":27,"area":"agents"},{"id":"2507.22827","title":"ScreenCoder: Advancing Visual-to-Code Generation for Front-End Automation via Modular Multimodal Agents","created":"2025-07-30","cited_by_count":26,"area":"agents"},{"id":"2402.05929","title":"An Interactive Agent Foundation Model","created":"2024-02-08","cited_by_count":25,"area":"agents"},{"id":"2503.17709","title":"GUI-Xplore: Empowering Generalizable GUI Agents with One Exploration","created":"2025-03-22","cited_by_count":25,"area":"agents"},{"id":"2403.08282","title":"Hierarchical Auto-Organizing System for Open-Ended Multi-Agent Navigation","created":"2024-03-13","cited_by_count":24,"area":"agents"},{"id":"2510.01354","title":"WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents","created":"2025-10-01","cited_by_count":24,"area":"agents"},{"id":"2503.12533","title":"Being-0: A Humanoid Robotic Agent with Vision-Language Models and Modular Skills","created":"2025-03-16","cited_by_count":22,"area":"agents"},{"id":"2601.12346","title":"MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents","created":"2026-01-18","cited_by_count":22,"area":"agents"},{"id":"2403.19622","title":"RH20T-P: A Primitive-Level Robotic Dataset Towards Composable Generalization Agents","created":"2024-03-28","cited_by_count":20,"area":"agents"},{"id":"2510.09038","title":"Auto-scaling Continuous Memory for GUI Agent","created":"2025-10-10","cited_by_count":20,"area":"agents"},{"id":"2404.04619","title":"Do We Really Need a Complex Agent System? Distill Embodied Agent into a Single Model","created":"2024-04-06","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":"2503.10120","title":"Hybrid Agents for Image Restoration","created":"2025-03-13","cited_by_count":17,"area":"agents"},{"id":"2504.16420","title":"A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigms","created":"2025-04-23","cited_by_count":17,"area":"agents"},{"id":"2407.20505","title":"Interpreting and Mitigating Hallucination in MLLMs through Multi-agent Debate","created":"2024-07-30","cited_by_count":16,"area":"agents"},{"id":"2403.14783","title":"Multi-Agent VQA: Exploring Multi-Agent Foundation Models in Zero-Shot Visual Question Answering","created":"2024-03-21","cited_by_count":15,"area":"agents"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2403.07952","title":"AesopAgent: Agent-driven Evolutionary System on Story-to-Video Production","created":"2024-03-12","cited_by_count":13,"area":"agents"},{"id":"2603.26512","title":"CADSmith: Multi-Agent CAD Generation with Programmatic Geometric Validation","created":"2026-03-27","cited_by_count":13,"area":"agents"},{"id":"2502.08556","title":"Human-Centric Foundation Models: Perception, Generation and Agentic Modeling","created":"2025-02-12","cited_by_count":12,"area":"agents"},{"id":"2410.20666","title":"Guide-LLM: An Embodied LLM Agent and Text-Based Topological Map for Robotic Guidance of People with Visual Impairments","created":"2024-10-28","cited_by_count":10,"area":"agents"},{"id":"2504.19276","title":"Anyprefer: An Agentic Framework for Preference Data Synthesis","created":"2025-04-27","cited_by_count":10,"area":"agents"},{"id":"2510.04017","title":"Zephyrus: An Agentic Framework for Weather Science","created":"2025-10-05","cited_by_count":10,"area":"agents"},{"id":"2306.08129","title":"AVIS: Autonomous Visual Information Seeking with Large Language Model Agent","created":"2023-06-13","cited_by_count":8,"area":"agents"},{"id":"2412.01250","title":"Collaborative Instance Object Navigation: Leveraging Uncertainty-Awareness to Minimize Human-Agent Dialogues","created":"2024-12-02","cited_by_count":8,"area":"agents"},{"id":"2505.09787","title":"A Multimodal Multi-Agent Framework for Radiology Report Generation","created":"2025-05-14","cited_by_count":8,"area":"agents"},{"id":"2505.12842","title":"GEM: Gaussian Embedding Modeling for Out-of-Distribution Detection in GUI Agents","created":"2025-05-19","cited_by_count":8,"area":"agents"},{"id":"2404.05465","title":"HAMMR: HierArchical MultiModal React agents for generic VQA","created":"2024-04-08","cited_by_count":7,"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":"2505.19662","title":"FieldWorkArena: Agentic AI Benchmark for Real Field Work Tasks","created":"2025-05-26","cited_by_count":6,"area":"agents"},{"id":"2506.18472","title":"AViLA: Asynchronous Vision-Language Agent for Streaming Multimodal Data Interaction","created":"2025-06-23","cited_by_count":6,"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":"2509.24380","title":"Agentic Services Computing","created":"2025-09-29","cited_by_count":6,"area":"agents"},{"id":"2512.14234","title":"ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body","created":"2025-12-16","cited_by_count":6,"area":"agents"},{"id":"2601.01891","title":"Agentic AI in Remote Sensing: Foundations, Taxonomy, and Emerging Systems","created":"2026-01-05","cited_by_count":6,"area":"agents"},{"id":"2505.15928","title":"ViQAgent: Zero-Shot Video Question Answering via Agent with Open-Vocabulary Grounding Validation","created":"2025-05-21","cited_by_count":5,"area":"agents"},{"id":"2505.19905","title":"EMAC+: Embodied Multimodal Agent for Collaborative Planning with VLM+LLM","created":"2025-05-26","cited_by_count":5,"area":"agents"},{"id":"2507.20145","title":"Multi-Agent Interactive Question Generation Framework for Long Document Understanding","created":"2025-07-27","cited_by_count":4,"area":"agents"},{"id":"2409.12089","title":"The Impact of Element Ordering on LM Agent Performance","created":"2024-09-18","cited_by_count":3,"area":"agents"},{"id":"2504.09532","title":"Humanoid Agent via Embodied Chain-of-Action Reasoning with Multimodal Foundation Models for Zero-Shot Loco-Manipulation","created":"2025-04-13","cited_by_count":3,"area":"agents"},{"id":"2508.15876","title":"DeepMEL: A Multi-Agent Collaboration Framework for Multimodal Entity Linking","created":"2025-08-21","cited_by_count":3,"area":"agents"},{"id":"2605.09317","title":"Mem-W: Latent Memory-Native GUI Agents","created":"2026-05-10","cited_by_count":3,"area":"agents"},{"id":"2605.16481","title":"Visual Agentic Memory: Enabling Online Long Video Understanding via Online Indexing, Hierarchical Memory, and Agentic Retrieval","created":"2026-05-15","cited_by_count":3,"area":"agents"},{"id":"2606.11977","title":"ParseFixer: An Agentic Framework for Document Parsing via Selective Multimodal Correction","created":"2026-06-10","cited_by_count":3,"area":"agents"},{"id":"2606.24470","title":"The Latent Bridge: A Continuous Slow-Fast Channel for Real-Time Game Agents","created":"2026-06-23","cited_by_count":3,"area":"agents"},{"id":"2606.28357","title":"ReasonRec: A Reasoning-Augmented Multimodal Agent for Unified Recommendation","created":"2026-06-08","cited_by_count":3,"area":"agents"},{"id":"2403.00833","title":"Position Paper: Agent AI Towards a Holistic Intelligence","created":"2024-02-28","cited_by_count":2,"area":"agents"},{"id":"2406.14917","title":"LLM2TEA: An Agentic AI Designer for Discovery with Generative Evolutionary Multitasking","created":"2024-06-21","cited_by_count":2,"area":"agents"},{"id":"2412.04090","title":"LossAgent: Towards Any Optimization Objectives for Image Processing with LLM Agents","created":"2024-12-05","cited_by_count":2,"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":"2606.13707","title":"Orchestra-o1: Omnimodal Agent Orchestration","created":"2026-06-10","cited_by_count":2,"area":"agents"},{"id":"2504.08531","title":"Embodied Image Captioning: Self-supervised Learning Agents for Spatially Coherent Image Descriptions","created":"2025-04-11","cited_by_count":1,"area":"agents"},{"id":"2508.18177","title":"Scene-Aware Vectorized Memory Multi-Agent Framework with Cross-Modal Differentiated Quantization VLMs for Visually Impaired Assistance","created":"2025-08-25","cited_by_count":1,"area":"agents"},{"id":"2509.22720","title":"LayoutAgent: A Vision-Language Agent Guided Compositional Diffusion for Spatial Layout Planning","created":"2025-09-24","cited_by_count":1,"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":"2608.20379","title":"A Survey on Foundations and Frontiers of Multimodal Agentic Frameworks: Techniques and Applications","created":"2026-06-28","cited_by_count":1,"area":"agents"},{"id":"2509.14627","title":"Towards Human-like Multimodal Conversational Agent by Generating Engaging Speech","created":"2025-09-18","cited_by_count":0,"area":"agents"},{"id":"2602.08949","title":"Digital Twin and Agentic AI for Wild Fire Disaster Management: Intelligent Virtual Situation Room","created":"2026-02-09","cited_by_count":0,"area":"agents"},{"id":"2602.23806","title":"See, Act, Adapt: Active Perception for Unsupervised Cross-Domain Visual Adaptation via Personalized VLM-Guided Agent","created":"2026-02-27","cited_by_count":0,"area":"agents"},{"id":"2604.06562","title":"On Emotion-Sensitive Decision Making of Small Language Model Agents","created":"2026-04-08","cited_by_count":0,"area":"agents"},{"id":"2604.07468","title":"M-ArtAgent: Evidence-Based Multimodal Agent for Implicit Art Influence Discovery","created":"2026-04-08","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":"2605.28629","title":"Mobile-Aptus: Confidence-Driven Proactive and Robust Interaction in MLLM-based Mobile-Using Agents","created":"2026-05-27","cited_by_count":0,"area":"agents"},{"id":"2606.12969","title":"Multi-Modal Agents for Power Distribution Defect Detection: An Evaluation of Foundation Models","created":"2026-06-11","cited_by_count":0,"area":"agents"},{"id":"2607.07383","title":"MMAgent-R$^2$: Learning to Rerank and Reject for Agentic mRAG","created":"2026-07-08","cited_by_count":0,"area":"agents"},{"id":"2608.10827","title":"MIRA: Medical Image Reflection for Agentic Diagnosis","created":"2026-08-11","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":"2609.16732","title":"When Agents See Differently: Exposing UI Desynchronization Threats in Mobile Agents","created":"2026-09-15","cited_by_count":0,"area":"agents"},{"id":"2609.20887","title":"BirdsongChat: A Hybrid Multi-Agent Framework for Multimodal Embodied Behavior Simulation","created":"2026-09-16","cited_by_count":0,"area":"agents"},{"id":"2609.26124","title":"MAC-RRG: Iterative Multi-Agent Collaboration for X-ray Radiology Report Generation","created":"2026-09-20","cited_by_count":0,"area":"agents"},{"id":"2610.04940","title":"Software World Models: From Consequence Prediction to Decision Value","created":"2026-10-04","cited_by_count":0,"area":"agents"}],"next_cursor":null}