{"total":41,"rows":[{"id":"2508.10833","title":"UI-Venus Technical Report: Building High-performance UI Agents with RFT","created":"2025-08-14","cited_by_count":93,"area":"agents"},{"id":"2507.19478","title":"MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents","created":"2025-07-25","cited_by_count":67,"area":"agents"},{"id":"2503.10200","title":"LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents","created":"2025-03-13","cited_by_count":58,"area":"agents"},{"id":"2505.19897","title":"ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows","created":"2025-05-26","cited_by_count":52,"area":"agents"},{"id":"2506.01300","title":"ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding","created":"2025-06-02","cited_by_count":50,"area":"agents"},{"id":"2511.07332","title":"Grounding Computer Use Agents on Human Demonstrations","created":"2025-11-10","cited_by_count":22,"area":"agents"},{"id":"2601.04786","title":"AgentOCR: Reimagining Agent History via Optical Self-Compression","created":"2026-01-08","cited_by_count":22,"area":"agents"},{"id":"2602.03411","title":"SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training","created":"2026-02-03","cited_by_count":22,"area":"agents"},{"id":"2505.11891","title":"Mobile-Bench-v2: A More Realistic and Comprehensive Benchmark for VLM-based Mobile Agents","created":"2025-05-17","cited_by_count":16,"area":"agents"},{"id":"2508.01415","title":"RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Interactive Environmental Learning in Physical Embodied Systems","created":"2025-08-02","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":"2505.07634","title":"Neural Brain: A Neuroscience-inspired Framework for Embodied Agents","created":"2025-05-12","cited_by_count":10,"area":"agents"},{"id":"2511.00810","title":"GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding","created":"2025-11-02","cited_by_count":8,"area":"agents"},{"id":"2511.14446","title":"Agentic Video Intelligence: A Flexible Framework for Advanced Video Exploration and Understanding","created":"2025-11-18","cited_by_count":7,"area":"agents"},{"id":"2512.16501","title":"VenusBench-GD: A Comprehensive Multi-Platform GUI Benchmark for Diverse Grounding Tasks","created":"2025-12-18","cited_by_count":7,"area":"agents"},{"id":"2505.24354","title":"Unifying Language Agent Algorithms with Graph-based Orchestration Engine for Reproducible Agent Research","created":"2025-05-30","cited_by_count":5,"area":"agents"},{"id":"2512.11611","title":"Using GUI Agent for Electronic Design Automation","created":"2025-12-12","cited_by_count":5,"area":"agents"},{"id":"2511.07315","title":"JPRO: Automated Multimodal Jailbreaking via Multi-Agent Collaboration Framework","created":"2025-11-10","cited_by_count":4,"area":"agents"},{"id":"2605.16883","title":"SE-GA: Memory-Augmented Self-Evolution for GUI Agents","created":"2026-05-16","cited_by_count":4,"area":"agents"},{"id":"2505.20148","title":"MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents","created":"2025-05-26","cited_by_count":3,"area":"agents"},{"id":"2506.04217","title":"OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis","created":"2025-06-04","cited_by_count":3,"area":"agents"},{"id":"2508.08764","title":"CARES: Collaborative Agentic Reasoning for Error Detection in Surgery","created":"2025-08-12","cited_by_count":3,"area":"agents"},{"id":"2604.07818","title":"Open-Ended Video Game Glitch Detection with Agentic Reasoning and Temporal Grounding","created":"2026-04-09","cited_by_count":3,"area":"agents"},{"id":"2605.03804","title":"ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Forgetting","created":"2026-05-05","cited_by_count":3,"area":"agents"},{"id":"2605.10286","title":"AgentRx: A Benchmark Study of LLM Agents for Multimodal Clinical Prediction Tasks","created":"2026-05-11","cited_by_count":3,"area":"agents"},{"id":"2509.24943","title":"Perceive, Verify and Understand Long Video: Multi-Granular Perception and Active Verification via Interactive Agents","created":"2025-09-29","cited_by_count":2,"area":"agents"},{"id":"2509.26006","title":"AgenticIQA: An Agentic Framework for Adaptive and Interpretable Image Quality Assessment","created":"2025-09-30","cited_by_count":2,"area":"agents"},{"id":"2512.03500","title":"EEA: Exploration-Exploitation Agent for Long Video Understanding","created":"2025-12-03","cited_by_count":2,"area":"agents"},{"id":"2609.11899","title":"Caption-once, Frames-on-Demand: Visual-Need Routing for Budget-Aware Agentic Long Video Understanding","created":"2026-09-10","cited_by_count":2,"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":"2508.06189","title":"MA-CBP: A Criminal Behavior Prediction Framework Based on Multi-Agent Asynchronous Collaboration","created":"2025-08-08","cited_by_count":0,"area":"agents"},{"id":"2510.18608","title":"A Compositional Paradigm for Foundation Models: Towards Smarter Robotic Agents","created":"2025-10-21","cited_by_count":0,"area":"agents"},{"id":"2605.04870","title":"VTAgent: Agentic Keyframe Anchoring for Evidence-Aware Video TextVQA","created":"2026-05-06","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":"2605.22366","title":"AgroTools: A Benchmark for Tool-Augmented Multimodal Agents in Agriculture","created":"2026-05-21","cited_by_count":0,"area":"agents"},{"id":"2605.31365","title":"Learning to Adapt: Self-Improving Web Agent via Cognitive-Aware Exploration","created":"2026-05-29","cited_by_count":0,"area":"agents"},{"id":"2607.00547","title":"EgoGapBench: Benchmarking Egocentric Action Selection in Multi-Agent Scenes","created":"2026-07-01","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":"2608.10827","title":"MIRA: Medical Image Reflection for Agentic Diagnosis","created":"2026-08-11","cited_by_count":0,"area":"agents"},{"id":"2608.27866","title":"Iron: Intent-Aligned and Retrospective Dual Learning Framework for Enhancing Generalist Virtual Agents","created":"2026-08-28","cited_by_count":0,"area":"agents"},{"id":"2610.19849","title":"DeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}