{"list":"other","total":78,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251},{"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":"2501.12326","title":"UI-TARS: Pioneering Automated GUI Interaction with Native Agents","created":"2025-01-21","cited_by_count":610},{"id":"2009.12293","title":"robosuite: A Modular Simulation Framework and Benchmark for Robot Learning","created":"2020-09-25","cited_by_count":511},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"2405.14573","title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","created":"2024-05-23","cited_by_count":468},{"id":"2504.20073","title":"RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning","created":"2025-04-24","cited_by_count":386},{"id":"2410.05243","title":"Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents","created":"2024-10-07","cited_by_count":382},{"id":"2410.23218","title":"OS-ATLAS: A Foundation Action Model for Generalist GUI Agents","created":"2024-10-30","cited_by_count":378},{"id":"2403.07718","title":"WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?","created":"2024-03-12","cited_by_count":363},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"2306.13831","title":"Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks","created":"2023-06-24","cited_by_count":327},{"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":"2412.04454","title":"Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction","created":"2024-12-05","cited_by_count":278},{"id":"2411.02337","title":"WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning","created":"2024-11-04","cited_by_count":256},{"id":"2504.10458","title":"GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents","created":"2025-04-14","cited_by_count":244},{"id":"2402.19446","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","created":"2024-02-29","cited_by_count":228},{"id":"2409.08264","title":"Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale","created":"2024-09-12","cited_by_count":223},{"id":"1502.02259","title":"Contextual Markov Decision Processes","created":"2015-02-08","cited_by_count":220},{"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":"2006.13760","title":"The NetHack Learning Environment","created":"2020-06-24","cited_by_count":198},{"id":"2302.02662","title":"Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning","created":"2023-02-06","cited_by_count":195},{"id":"2406.03679","title":"On the Effects of Data Scale on UI Control Agents","created":"2024-06-06","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":"2505.22648","title":"WebDancer: Towards Autonomous Information Seeking Agency","created":"2025-05-28","cited_by_count":188},{"id":"2308.15272","title":"AutoDroid: LLM-powered Task Automation in Android","created":"2023-08-29","cited_by_count":184},{"id":"2107.12808","title":"Open-Ended Learning Leads to Generally Capable Agents","created":"2021-07-27","cited_by_count":182},{"id":"2005.03776","title":"Mapping Natural Language Instructions to Mobile UI Action Sequences","created":"2020-05-07","cited_by_count":181},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170},{"id":"2503.21620","title":"UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning","created":"2025-03-27","cited_by_count":168},{"id":"2505.16421","title":"WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning","created":"2025-05-22","cited_by_count":165},{"id":"2412.19723","title":"OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis","created":"2024-12-27","cited_by_count":163},{"id":"2504.00906","title":"Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents","created":"2025-04-01","cited_by_count":159},{"id":"2405.10292","title":"Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning","created":"2024-05-16","cited_by_count":158},{"id":"2412.16256","title":"Aria-UI: Visual Grounding for GUI Instructions","created":"2024-12-20","cited_by_count":140},{"id":"2504.14239","title":"InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners","created":"2025-04-19","cited_by_count":140},{"id":"2011.13389","title":"Generalization in Reinforcement Learning by Soft Data Augmentation","created":"2020-11-26","cited_by_count":137},{"id":"2404.06474","title":"Autonomous Evaluation and Refinement of Digital Agents","created":"2024-04-09","cited_by_count":137},{"id":"1810.12282","title":"Assessing Generalization in Deep Reinforcement Learning","created":"2018-10-29","cited_by_count":133},{"id":"2501.11733","title":"Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks","created":"2025-01-20","cited_by_count":131},{"id":"2407.17490","title":"AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents","created":"2024-07-03","cited_by_count":113},{"id":"2411.04890","title":"GUI Agents with Foundation Models: A Comprehensive Survey","created":"2024-11-07","cited_by_count":111},{"id":"2504.09037","title":"A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems","created":"2025-04-12","cited_by_count":111},{"id":"2010.04296","title":"CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning","created":"2020-10-08","cited_by_count":109},{"id":"2301.08028","title":"A Tutorial on Meta-Reinforcement Learning","created":"2023-01-19","cited_by_count":108},{"id":"2504.08942","title":"AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories","created":"2025-04-11","cited_by_count":108},{"id":"2410.24024","title":"AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents","created":"2024-10-31","cited_by_count":107},{"id":"2408.06327","title":"VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents","created":"2024-08-12","cited_by_count":103},{"id":"2411.00820","title":"AutoGLM: Autonomous Foundation Agents for GUIs","created":"2024-10-28","cited_by_count":100},{"id":"2105.13231","title":"AndroidEnv: A Reinforcement Learning Platform for Android","created":"2021-05-27","cited_by_count":90},{"id":"2205.11029","title":"META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI","created":"2022-05-23","cited_by_count":81},{"id":"2410.15164","title":"SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation","created":"2024-10-19","cited_by_count":81},{"id":"2410.16464","title":"Beyond Browsing: API-Based Web Agents","created":"2024-10-21","cited_by_count":78},{"id":"2505.16282","title":"ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay","created":"2025-05-22","cited_by_count":77},{"id":"2408.11824","title":"AppAgent v2: Advanced Agent for Flexible Mobile Interactions","created":"2024-08-05","cited_by_count":68},{"id":"2209.08199","title":"ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots","created":"2022-09-16","cited_by_count":66},{"id":"2510.16907","title":"VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents","created":"2025-10-19","cited_by_count":62},{"id":"2402.06596","title":"Understanding the Weakness of Large Language Model Agents within a Complex Android Environment","created":"2024-02-09","cited_by_count":60},{"id":"2404.16660","title":"Benchmarking Mobile Device Control Agents across Diverse Configurations","created":"2024-04-25","cited_by_count":55},{"id":"2507.05720","title":"MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment","created":"2025-07-08","cited_by_count":52},{"id":"2505.23762","title":"ZeroGUI: Automating Online GUI Learning at Zero Human Cost","created":"2025-05-29","cited_by_count":44},{"id":"2506.03533","title":"Go-Browse: Training Web Agents with Structured Exploration","created":"2025-06-04","cited_by_count":33},{"id":"2504.19838","title":"LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects","created":"2025-04-28","cited_by_count":32},{"id":"2411.02006","title":"Foundations and Recent Trends in Multimodal Mobile Agents: A Survey","created":"2024-11-04","cited_by_count":31},{"id":"2503.11069","title":"API Agents vs. GUI Agents: Divergence and Convergence","created":"2025-03-14","cited_by_count":29},{"id":"2110.02102","title":"CARL: A Benchmark for Contextual and Adaptive Reinforcement Learning","created":"2021-10-05","cited_by_count":21},{"id":"2507.04103","title":"How to Train Your LLM Web Agent: A Statistical Diagnosis","created":"2025-07-05","cited_by_count":19},{"id":"2506.20332","title":"Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training","created":"2025-06-25","cited_by_count":17},{"id":"2502.06395","title":"AppVLM: A Lightweight Vision Language Model for Online App Control","created":"2025-02-10","cited_by_count":15},{"id":"2512.19918","title":"Widget2Code: From Visual Widgets to UI Code via Multimodal LLMs","created":"2025-12-22","cited_by_count":9}],"next_cursor":null}