{"total":363,"rows":[{"id":"2407.16741","title":"OpenHands: An Open Platform for AI Software Developers as Generalist Agents","created":"2024-07-23","cited_by_count":1002,"area":"agents"},{"id":"2405.14573","title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","created":"2024-05-23","cited_by_count":468,"area":null},{"id":"2409.07429","title":"Agent Workflow Memory","created":"2024-09-11","cited_by_count":383,"area":"agents"},{"id":"2412.14161","title":"TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks","created":"2024-12-18","cited_by_count":326,"area":"agents"},{"id":"2409.08264","title":"Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale","created":"2024-09-12","cited_by_count":223,"area":"agents"},{"id":"2407.01502","title":"AI Agents That Matter","created":"2024-07-01","cited_by_count":219,"area":null},{"id":"2503.16416","title":"Survey on Evaluation of LLM-based Agents","created":"2025-03-20","cited_by_count":204,"area":"agents"},{"id":"2411.18279","title":"Large Language Model-Brained GUI Agents: A Survey","created":"2024-11-27","cited_by_count":162,"area":"agents"},{"id":"2412.05467","title":"The BrowserGym Ecosystem for Web Agent Research","created":"2024-12-06","cited_by_count":161,"area":"agents"},{"id":"2508.09123","title":"OpenCUA: Open Foundations for Computer-Use Agents","created":"2025-08-12","cited_by_count":160,"area":"mllm"},{"id":"2407.15711","title":"AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?","created":"2024-07-22","cited_by_count":158,"area":"agents"},{"id":"2407.01476","title":"Tree Search for Language Model Agents","created":"2024-07-01","cited_by_count":151,"area":"agents"},{"id":"2505.13227","title":"Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis","created":"2025-05-19","cited_by_count":139,"area":"agents"},{"id":"2410.06703","title":"ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents","created":"2024-10-09","cited_by_count":133,"area":"agents"},{"id":"2412.09605","title":"AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials","created":"2024-12-12","cited_by_count":130,"area":"agents"},{"id":"2410.13232","title":"Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation","created":"2024-10-17","cited_by_count":126,"area":"wm"},{"id":"2406.12373","title":"WebCanvas: Benchmarking Web Agents in Online Environments","created":"2024-06-18","cited_by_count":121,"area":"agents"},{"id":"2406.12814","title":"Dissecting Adversarial Robustness of Multimodal LM Agents","created":"2024-06-18","cited_by_count":120,"area":"agents"},{"id":"2504.06821","title":"Inducing Programmatic Skills for Agentic Tasks","created":"2025-04-09","cited_by_count":111,"area":"agents"},{"id":"2504.08942","title":"AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories","created":"2025-04-11","cited_by_count":108,"area":"agents"},{"id":"2408.06327","title":"VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents","created":"2024-08-12","cited_by_count":103,"area":"mllm"},{"id":"2412.13501","title":"GUI Agents: A Survey","created":"2024-12-18","cited_by_count":103,"area":"agents"},{"id":"2503.04957","title":"SafeArena: Evaluating the Safety of Autonomous Web Agents","created":"2025-03-06","cited_by_count":102,"area":"agents"},{"id":"2501.07278","title":"Lifelong Learning of Large Language Model based Agents: A Roadmap","created":"2025-01-13","cited_by_count":83,"area":"agents"},{"id":"2410.16464","title":"Beyond Browsing: API-Based Web Agents","created":"2024-10-21","cited_by_count":78,"area":"agents"},{"id":"2503.15661","title":"UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction","created":"2025-03-19","cited_by_count":77,"area":null},{"id":"2411.02305","title":"CRMArena: Understanding the Capacity of LLM Agents to Perform Professional CRM Tasks in Realistic Environments","created":"2024-11-04","cited_by_count":71,"area":"agents"},{"id":"2410.13886","title":"Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents","created":"2024-10-11","cited_by_count":65,"area":"agents"},{"id":"2412.15701","title":"Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration","created":"2024-12-20","cited_by_count":65,"area":"agents"},{"id":"2602.02475","title":"AgentRx: Diagnosing AI Agent Failures from Execution Trajectories","created":"2026-02-02","cited_by_count":60,"area":"agents"},{"id":"2410.02907","title":"NNetNav: Unsupervised Learning of Browser Agents Through Environment Interaction in the Wild","created":"2024-10-03","cited_by_count":59,"area":"agents"},{"id":"2508.09124","title":"OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflows","created":"2025-08-12","cited_by_count":57,"area":"agents"},{"id":"2407.10956","title":"Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?","created":"2024-07-15","cited_by_count":56,"area":"agents"},{"id":"2405.00823","title":"WorkBench: a Benchmark Dataset for Agents in a Realistic Workplace Setting","created":"2024-05-01","cited_by_count":53,"area":"agents"},{"id":"2601.12538","title":"A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents","created":"2026-01-18","cited_by_count":50,"area":"lr"},{"id":"2506.06698","title":"Contextual Experience Replay for Self-Improvement of Language Agents","created":"2025-06-07","cited_by_count":48,"area":"agents"},{"id":"2505.18878","title":"CRMArena-Pro: Holistic Assessment of LLM Agents Across Diverse Business Scenarios and Interactions","created":"2025-05-24","cited_by_count":47,"area":"agents"},{"id":"2605.18747","title":"Code as Agent Harness","created":"2026-05-18","cited_by_count":47,"area":"agents"},{"id":"2506.14205","title":"AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents","created":"2025-06-17","cited_by_count":46,"area":"agents"},{"id":"2506.23719","title":"DABstep: Data Agent Benchmark for Multi-step Reasoning","created":"2025-06-30","cited_by_count":46,"area":"lr"},{"id":"2410.19100","title":"VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks","created":"2024-10-24","cited_by_count":43,"area":null},{"id":"2505.07782","title":"MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering","created":"2025-05-12","cited_by_count":41,"area":"agents"},{"id":"2505.15277","title":"Web-Shepherd: Advancing PRMs for Reinforcing Web Agents","created":"2025-05-21","cited_by_count":41,"area":"agents"},{"id":"2505.19683","title":"Large Language Models for Planning: A Comprehensive and Systematic Survey","created":"2025-05-26","cited_by_count":40,"area":"lr"},{"id":"2411.15004","title":"ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data","created":"2024-11-22","cited_by_count":39,"area":"agents"},{"id":"2605.10912","title":"WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation","created":"2026-05-11","cited_by_count":37,"area":"agents"},{"id":"2501.16609","title":"CowPilot: A Framework for Autonomous and Human-Agent Collaborative Web Navigation","created":"2025-01-28","cited_by_count":36,"area":"agents"},{"id":"2508.04482","title":"OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use","created":"2025-08-06","cited_by_count":35,"area":"agents"},{"id":"2503.05659","title":"A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrieval","created":"2025-03-07","cited_by_count":33,"area":"agents"},{"id":"2504.18875","title":"Generative to Agentic AI: Survey, Conceptualization, and Challenges","created":"2025-04-26","cited_by_count":33,"area":"agents"},{"id":"2506.03533","title":"Go-Browse: Training Web Agents with Structured Exploration","created":"2025-06-04","cited_by_count":33,"area":"agents"},{"id":"2602.11964","title":"Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments","created":"2026-02-12","cited_by_count":33,"area":"agents"},{"id":"2604.05172","title":"ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces","created":"2026-04-06","cited_by_count":33,"area":"agents"},{"id":"2502.06776","title":"InSTA: Towards Internet-Scale Training For Agents","created":"2025-02-10","cited_by_count":32,"area":"agents"},{"id":"2504.14064","title":"DoomArena: A framework for Testing AI Agents Against Evolving Security Threats","created":"2025-04-18","cited_by_count":32,"area":"agents"},{"id":"2506.04135","title":"macOSWorld: A Multilingual Interactive Benchmark for GUI Agents","created":"2025-06-04","cited_by_count":32,"area":"agents"},{"id":"2506.01952","title":"WebChoreArena: Evaluating Web Browsing Agents on Realistic Tedious Web Tasks","created":"2025-06-02","cited_by_count":30,"area":"agents"},{"id":"2510.24563","title":"OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents","created":"2025-10-28","cited_by_count":29,"area":"lr"},{"id":"2502.20383","title":"Why Are Web AI Agents More Vulnerable Than Standalone LLMs? A Security Analysis","created":"2025-02-27","cited_by_count":27,"area":"agents"},{"id":"2604.09408","title":"HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?","created":"2026-04-10","cited_by_count":27,"area":"agents"},{"id":"2506.04405","title":"MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science","created":"2025-06-04","cited_by_count":23,"area":"lr"},{"id":"2506.23139","title":"Benchmarking Deep Search over Heterogeneous Enterprise Data","created":"2025-06-29","cited_by_count":23,"area":"lr"},{"id":"2605.12493","title":"LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues","created":"2026-05-12","cited_by_count":23,"area":"agents"},{"id":"2606.17573","title":"Cordon: Semantic Transactions for Tool-Using LLM Agents","created":"2026-06-16","cited_by_count":22,"area":"agents"},{"id":"2604.24964","title":"Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks","created":"2026-04-27","cited_by_count":21,"area":"agents"},{"id":"2510.17797","title":"Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics","created":"2025-10-20","cited_by_count":20,"area":null},{"id":"2602.05073","title":"Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities","created":"2026-02-04","cited_by_count":20,"area":"agents"},{"id":"2510.22780","title":"How Do AI Agents Do Human Work? Comparing AI and Human Workflows Across Diverse Occupations","created":"2025-10-26","cited_by_count":19,"area":null},{"id":"2601.06007","title":"Don't Break the Cache: An Evaluation of Prompt Caching for Long-Horizon Agentic Tasks","created":"2026-01-09","cited_by_count":19,"area":"agents"},{"id":"2604.08516","title":"MolmoWeb: Open Visual Web Agent and Open Data for the Open Web","created":"2026-04-09","cited_by_count":19,"area":"agents"},{"id":"2506.10953","title":"Build the web for agents, not agents for the web","created":"2025-06-12","cited_by_count":18,"area":"agents"},{"id":"2607.10487","title":"Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents","created":"2026-07-11","cited_by_count":18,"area":"agents"},{"id":"2503.10689","title":"Learning to Contextualize Web Pages for Enhanced Decision Making by LLM Agents","created":"2025-03-12","cited_by_count":17,"area":"agents"},{"id":"2510.24702","title":"Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents","created":"2025-10-28","cited_by_count":17,"area":"agents"},{"id":"2510.27287","title":"Can LLMs Help You at Work? A Sandbox for Evaluating LLM Agents in Enterprise Environments","created":"2025-10-31","cited_by_count":17,"area":"agents"},{"id":"2604.23781","title":"ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents","created":"2026-04-26","cited_by_count":17,"area":"agents"},{"id":"2507.21017","title":"MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them","created":"2025-07-28","cited_by_count":16,"area":"agents"},{"id":"2510.01524","title":"WALT: Web Agents that Learn Tools","created":"2025-10-01","cited_by_count":16,"area":"lr"},{"id":"2510.03204","title":"FocusAgent: Simple Yet Effective Ways of Trimming the Large Context of Web Agents","created":"2025-10-03","cited_by_count":16,"area":"agents"},{"id":"2607.13988","title":"TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents","created":"2026-07-15","cited_by_count":16,"area":null},{"id":"2506.15677","title":"Embodied Web Agents: Bridging Physical-Digital Realms for Integrated Agent Intelligence","created":"2025-06-18","cited_by_count":15,"area":"agents"},{"id":"2510.03285","title":"WAREX: Web Agent Reliability Evaluation on Existing Benchmarks","created":"2025-09-28","cited_by_count":15,"area":"agents"},{"id":"2512.22894","title":"DECEPTICON: How Dark Patterns Manipulate Web Agents","created":"2025-12-28","cited_by_count":15,"area":"agents"},{"id":"2603.13594","title":"EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings","created":"2026-03-13","cited_by_count":15,"area":"agents"},{"id":"2501.12485","title":"R2D2: Remembering, Replaying and Dynamic Decision Making with a Reflective Agentic Memory","created":"2025-01-21","cited_by_count":14,"area":"agents"},{"id":"2503.02950","title":"LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications","created":"2025-03-04","cited_by_count":14,"area":"agents"},{"id":"2507.14799","title":"Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility Tree","created":"2025-07-20","cited_by_count":14,"area":"agents"},{"id":"2602.07918","title":"CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution","created":"2026-02-08","cited_by_count":14,"area":"agents"},{"id":"2603.22862","title":"The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration","created":"2026-03-24","cited_by_count":14,"area":"agents"},{"id":"2412.08445","title":"TapeAgents: a Holistic Framework for Agent Development and Optimization","created":"2024-12-11","cited_by_count":13,"area":"agents"},{"id":"2504.10127","title":"Breaking the Data Barrier -- Building GUI Agents Through Task Generalization","created":"2025-04-14","cited_by_count":13,"area":"agents"},{"id":"2506.11102","title":"Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey","created":"2025-06-06","cited_by_count":13,"area":"agents"},{"id":"2507.23773","title":"General Agentic Planning Through Simulative Reasoning with World Models","created":"2025-07-31","cited_by_count":13,"area":"wm"},{"id":"2603.20340","title":"ContractSkill: Repairable Contract-Based Skills for Multimodal Web Agents","created":"2026-03-20","cited_by_count":13,"area":"agents"},{"id":"2604.06240","title":"The Art of Building Verifiers for Computer Use Agents","created":"2026-04-05","cited_by_count":13,"area":"agents"},{"id":"2604.09937","title":"HealthAdminBench: Evaluating Computer-Use Agents on Healthcare Administration Tasks","created":"2026-04-10","cited_by_count":13,"area":"agents"},{"id":"2409.01927","title":"From Grounding to Planning: Benchmarking Bottlenecks in Web Agents","created":"2024-09-03","cited_by_count":12,"area":"agents"},{"id":"2505.17767","title":"Position: The Real Barrier to LLM Agent Usability is Agentic ROI","created":"2025-05-23","cited_by_count":12,"area":"agents"},{"id":"2506.08972","title":"Atomic-to-Compositional Generalization for Mobile Agents with A New Benchmark and Scheduling System","created":"2025-06-10","cited_by_count":12,"area":"agents"},{"id":"2509.25609","title":"A Framework for Studying AI Agent Behavior: Evidence from Consumer Choice Experiments","created":"2025-09-30","cited_by_count":12,"area":"agents"}],"next_cursor":"100"}