{"total":34,"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":"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":"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":"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":"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":"2509.17158","title":"ARE: Scaling Up Agent Environments and Evaluations","created":"2025-09-21","cited_by_count":30,"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":"2508.16260","title":"MCPVerse: An Expansive, Real-World Benchmark for Agentic Tool Use","created":"2025-08-22","cited_by_count":16,"area":"agents"},{"id":"2601.14192","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","created":"2026-01-20","cited_by_count":16,"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":"2507.14447","title":"Routine: A Structural Planning Framework for LLM Agent System in Enterprise","created":"2025-07-19","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":"2601.08276","title":"ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Web","created":"2026-01-13","cited_by_count":7,"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":"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":"2510.02271","title":"InfoMosaic-Bench: Evaluating Multi-Source Information Seeking in Tool-Augmented Agents","created":"2025-10-02","cited_by_count":3,"area":"agents"},{"id":"2512.03955","title":"Benchmark for Planning and Control with Large Language Model Agents: Blocksworld with Model Context Protocol","created":"2025-12-03","cited_by_count":3,"area":"agents"},{"id":"2602.14281","title":"MCPShield: A Security Cognition Layer for Adaptive Trust Calibration in Model Context Protocol Agents","created":"2026-02-15","cited_by_count":3,"area":"agents"},{"id":"2604.11557","title":"UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents","created":"2026-04-13","cited_by_count":3,"area":"agents"},{"id":"2511.21758","title":"A Longitudinal Measurement of Privacy Policy Evolution for Large Language Models","created":"2025-11-24","cited_by_count":2,"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":"2508.13774","title":"Agentic DraCor and the Art of Docstring Engineering: Evaluating MCP-empowered LLM Usage of the DraCor API","created":"2025-08-19","cited_by_count":0,"area":"agents"},{"id":"2508.19500","title":"Servant, Stalker, Predator: How An Honest, Helpful, And Harmless (3H) Agent Unlocks Adversarial Skills","created":"2025-08-27","cited_by_count":0,"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":"2602.23367","title":"HumanMCP: A Human-Like Query Dataset for Evaluating MCP Tool Retrieval Performance","created":"2025-12-18","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":"2608.26199","title":"Benchmarking AI Agents for Hardware Design Automation via MCP Tool Calling","created":"2026-08-25","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"}],"next_cursor":null}