{"total":25,"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":"2602.00933","title":"MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers","created":"2026-01-31","cited_by_count":53,"area":"agents"},{"id":"2508.01780","title":"LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?","created":"2025-08-03","cited_by_count":48,"area":"agents"},{"id":"2509.09734","title":"MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools","created":"2025-09-10","cited_by_count":32,"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":"2508.15760","title":"LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries","created":"2025-08-21","cited_by_count":17,"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":"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":"2511.17729","title":"M^3-Bench: Multi-Modal, Multi-Hop, Multi-Threaded Tool-Using MLLM Agent Benchmark","created":"2025-11-21","cited_by_count":11,"area":"agents"},{"id":"2603.29139","title":"SciVisAgentBench: A Benchmark for Evaluating Scientific Data Analysis and Visualization Agents","created":"2026-03-31","cited_by_count":10,"area":"agents"},{"id":"2510.19286","title":"TheMCPCompany: Creating General-purpose Agents with Task-specific Tools","created":"2025-10-22","cited_by_count":4,"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":"2607.01084","title":"Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Use","created":"2026-07-01","cited_by_count":4,"area":"agents"},{"id":"2606.02470","title":"MCP-Persona: Benchmarking LLM Agents on Real-World Personal Applications via Environment Simulation","created":"2026-06-01","cited_by_count":3,"area":"agents"},{"id":"2606.20661","title":"From Knowing to Acting: Benchmarking Self-Awareness Capability of LLM Agents","created":"2026-06-09","cited_by_count":2,"area":"agents"},{"id":"2607.23722","title":"E-Bench: Benchmarking Multi-Step Tool-Use Agents in Real-World Product Scenarios","created":"2026-07-26","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":"2603.21630","title":"EnterpriseLab: A Full-Stack Platform for developing and deploying agents in Enterprises","created":"2026-03-23","cited_by_count":1,"area":"agents"},{"id":"2510.19423","title":"ETOM: A Five-Level Benchmark for Evaluating Tool Orchestration within the MCP Ecosystem","created":"2025-10-22","cited_by_count":0,"area":"agents"},{"id":"2601.17435","title":"Towards a Declarative Agentic Layer for Intelligent Agents in MCP-Based Server Ecosystems","created":"2026-01-24","cited_by_count":0,"area":"agents"},{"id":"2607.14642","title":"MCPEvol-Bench: Benchmarking LLM Agent Performance Across Dynamic Evolutions of MCP Servers","created":"2026-07-16","cited_by_count":0,"area":"agents"},{"id":"2609.13353","title":"SkillAtlas: An Attack Trace Library for Agent Skills","created":"2026-09-11","cited_by_count":0,"area":"agents"},{"id":"2610.16117","title":"Beyond Perfect Teammates: Multi-Agent Collaboration with Unreliable Colleagues","created":"2026-10-12","cited_by_count":0,"area":"agents"}],"next_cursor":null}