{"total":30,"rows":[{"id":"2508.20453","title":"MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers","created":"2025-08-28","cited_by_count":109,"area":"agents"},{"id":"2510.25726","title":"The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution","created":"2025-10-29","cited_by_count":85,"area":"agents"},{"id":"2512.19432","title":"MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments","created":"2025-12-22","cited_by_count":72,"area":"agents"},{"id":"2510.01179","title":"TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments","created":"2025-10-01","cited_by_count":69,"area":"agents"},{"id":"2508.13220","title":"MCPSecBench: A Systematic Security Benchmark and Playground for Testing Model Context Protocols","created":"2025-08-17","cited_by_count":51,"area":"agents"},{"id":"2507.12806","title":"MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models","created":"2025-07-17","cited_by_count":36,"area":"agents"},{"id":"2603.00718","title":"SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?","created":"2026-02-28","cited_by_count":30,"area":"agents"},{"id":"2603.22386","title":"From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents","created":"2026-03-23","cited_by_count":24,"area":"agents"},{"id":"2602.14878","title":"Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions","created":"2026-02-16","cited_by_count":17,"area":"agents"},{"id":"2512.08769","title":"A Practical Guide for Designing, Developing, and Deploying Production-Grade Agentic AI Workflows","created":"2025-12-09","cited_by_count":15,"area":"agents"},{"id":"2606.20683","title":"From Question Answering to Task Completion: A Survey on Agent System and Harness Design","created":"2026-06-14","cited_by_count":12,"area":"agents"},{"id":"2510.24284","title":"MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP Tools","created":"2025-10-28","cited_by_count":11,"area":"agents"},{"id":"2605.12481","title":"ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents","created":"2026-05-12","cited_by_count":11,"area":"agents"},{"id":"2511.13248","title":"DualTAP: A Dual-Task Adversarial Protector for Mobile MLLM Agents","created":"2025-11-17","cited_by_count":9,"area":"agents"},{"id":"2512.24565","title":"MCPAgentBench: A Real-world Task Benchmark for Evaluating LLM Agent MCP Tool Use","created":"2025-12-31","cited_by_count":9,"area":"agents"},{"id":"2602.10122","title":"A Practical Guide to Agentic AI Transition in Organizations","created":"2026-01-27","cited_by_count":5,"area":"agents"},{"id":"2605.10787","title":"ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox","created":"2026-05-11","cited_by_count":4,"area":"agents"},{"id":"2601.08173","title":"The Agent's First Day: Benchmarking Learning, Exploration, and Scheduling in the Workplace Scenarios","created":"2026-01-13","cited_by_count":3,"area":"agents"},{"id":"2604.09815","title":"EE-MCP: Self-Evolving MCP-GUI Agents via Automated Environment Generation and Experience Learning","created":"2026-04-10","cited_by_count":3,"area":"agents"},{"id":"2604.27955","title":"GUI Agents with Reinforcement Learning: Toward Digital Inhabitants","created":"2026-04-30","cited_by_count":3,"area":"agents"},{"id":"2608.03327","title":"Screenshots or Tools? Eliciting Tool Use and Managing Multimodal Context in Hybrid GUI-MCP Computer-Use Agents","created":"2026-08-04","cited_by_count":3,"area":"agents"},{"id":"2604.09587","title":"MobiFlow: Real-World Mobile Agent Benchmarking through Trajectory Fusion","created":"2026-02-28","cited_by_count":2,"area":"agents"},{"id":"2608.01684","title":"GABench: A Comprehensive Benchmark for Evaluating LLM Agents on Graph Analysis Tasks","created":"2026-08-03","cited_by_count":2,"area":"agents"},{"id":"2608.30478","title":"Agents in the Large: Perception-Centered Architecture for Persistent Agents","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2512.09706","title":"Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning","created":"2025-12-10","cited_by_count":0,"area":"agents"},{"id":"2607.20531","title":"DynamicMCPBench: A Trace-Grounded, Effect-Scored Benchmark for LLM Agents over Live MCP Servers","created":"2026-07-10","cited_by_count":0,"area":"agents"},{"id":"2609.30717","title":"RecToolBench: Benchmarking Recommendation-Specific Tool Orchestration under Fuzzy User Intent","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2609.35671","title":"PhoneCLI: From App Interfaces to Callable Commands for Mobile Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.38008","title":"HybridCUA: Learning to Orchestrate GUI and CLI for Computer-Use Agents","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.14157","title":"OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools","created":"2026-10-09","cited_by_count":0,"area":"agents"}],"next_cursor":null}