{"list":"other","total":51,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251},{"id":"2306.06070","title":"Mind2Web: Towards a Generalist Agent for the Web","created":"2023-06-09","cited_by_count":1242},{"id":"2404.07972","title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","created":"2024-04-11","cited_by_count":1195},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2312.08914","title":"CogAgent: A Visual Language Model for GUI Agents","created":"2023-12-14","cited_by_count":704},{"id":"2401.10935","title":"SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents","created":"2024-01-17","cited_by_count":567},{"id":"2401.01614","title":"GPT-4V(ision) is a Generalist Web Agent, if Grounded","created":"2024-01-03","cited_by_count":563},{"id":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509},{"id":"2405.14573","title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","created":"2024-05-23","cited_by_count":468},{"id":"2401.13919","title":"WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models","created":"2024-01-25","cited_by_count":438},{"id":"2311.08046","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","created":"2023-11-14","cited_by_count":371},{"id":"2307.12856","title":"A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis","created":"2023-07-24","cited_by_count":353},{"id":"2307.10088","title":"Android in the Wild: A Large-Scale Dataset for Android Device Control","created":"2023-07-19","cited_by_count":319},{"id":"2401.16158","title":"Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception","created":"2024-01-29","cited_by_count":293},{"id":"2403.09611","title":"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training","created":"2024-03-14","cited_by_count":232},{"id":"2409.08264","title":"Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale","created":"2024-09-12","cited_by_count":223},{"id":"2406.11896","title":"DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning","created":"2024-06-14","cited_by_count":214},{"id":"2402.07456","title":"OS-Copilot: Towards Generalist Computer Agents with Self-Improvement","created":"2024-02-12","cited_by_count":205},{"id":"2406.08451","title":"GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices","created":"2024-06-12","cited_by_count":194},{"id":"2406.01014","title":"Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration","created":"2024-06-03","cited_by_count":189},{"id":"2306.07863","title":"Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control","created":"2023-06-13","cited_by_count":187},{"id":"2308.15272","title":"AutoDroid: LLM-powered Task Automation in Android","created":"2023-08-29","cited_by_count":184},{"id":"2404.05719","title":"Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs","created":"2024-04-08","cited_by_count":176},{"id":"2402.17553","title":"OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web","created":"2024-02-27","cited_by_count":157},{"id":"2402.07939","title":"UFO: A UI-Focused Agent for Windows OS Interaction","created":"2024-02-08","cited_by_count":148},{"id":"2406.12373","title":"WebCanvas: Benchmarking Web Agents in Online Environments","created":"2024-06-18","cited_by_count":121},{"id":"2404.03413","title":"MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens","created":"2024-04-04","cited_by_count":118},{"id":"2407.17490","title":"AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents","created":"2024-07-03","cited_by_count":113},{"id":"2408.06327","title":"VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents","created":"2024-08-12","cited_by_count":103},{"id":"2101.09465","title":"WebSRC: A Dataset for Web-Based Structural Reading Comprehension","created":"2021-01-23","cited_by_count":100},{"id":"2404.05955","title":"VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?","created":"2024-04-09","cited_by_count":100},{"id":"2404.07973","title":"Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models","created":"2024-04-11","cited_by_count":97},{"id":"2105.13231","title":"AndroidEnv: A Reinforcement Learning Platform for Android","created":"2021-05-27","cited_by_count":90},{"id":"2407.13032","title":"Agent-E: From Autonomous Web Navigation to Foundational Design Principles in Agentic Systems","created":"2024-07-17","cited_by_count":81},{"id":"2409.20566","title":"MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning","created":"2024-09-30","cited_by_count":76},{"id":"2408.11824","title":"AppAgent v2: Advanced Agent for Flexible Mobile Interactions","created":"2024-08-05","cited_by_count":68},{"id":"2309.08172","title":"LASER: LLM Agent with State-Space Exploration for Web Navigation","created":"2023-09-15","cited_by_count":66},{"id":"2407.20183","title":"MindSearch: Mimicking Human Minds Elicits Deep AI Searcher","created":"2024-07-29","cited_by_count":66},{"id":"2406.08184","title":"MobileAgentBench: An Efficient and User-Friendly Benchmark for Mobile LLM Agents","created":"2024-06-12","cited_by_count":63},{"id":"2209.14927","title":"Spotlight: Mobile UI Understanding using Vision-Language Models with a Focus","created":"2022-09-29","cited_by_count":62},{"id":"2301.13280","title":"WebUI: A Dataset for Enhancing Visual UI Understanding with Web Semantics","created":"2023-01-30","cited_by_count":47},{"id":"2312.13108","title":"ASSISTGUI: Task-Oriented Desktop Graphical User Interface Automation","created":"2023-12-20","cited_by_count":45},{"id":"2403.17918","title":"AgentStudio: A Toolkit for Building General Virtual Agents","created":"2024-03-26","cited_by_count":45},{"id":"2406.10819","title":"GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding","created":"2024-06-16","cited_by_count":43},{"id":"2407.01511","title":"CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents","created":"2024-07-01","cited_by_count":39},{"id":"2407.04346","title":"MobileFlow: A Multimodal LLM For Mobile GUI Agent","created":"2024-07-05","cited_by_count":32},{"id":"2404.16048","title":"GUIDE: Graphical User Interface Data for Execution","created":"2024-04-09","cited_by_count":7}],"next_cursor":null}