{"total":35,"rows":[{"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":"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":"2511.01854","title":"Tool-to-Agent Retrieval: Bridging Tools and Agents for Scalable LLM Multi-Agent Systems","created":"2025-11-03","cited_by_count":15,"area":"agents"},{"id":"2601.20144","title":"Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents","created":"2026-01-28","cited_by_count":14,"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":"2606.22388","title":"PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems","created":"2026-06-21","cited_by_count":11,"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":"2603.05637","title":"Real Faults in Model Context Protocol (MCP) Software: a Comprehensive Taxonomy","created":"2026-03-05","cited_by_count":6,"area":"agents"},{"id":"2511.09572","title":"SynthTools: A Framework for Scaling Synthetic Tools for Agent Development","created":"2025-11-11","cited_by_count":5,"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":"2604.10015","title":"FinTrace: Holistic Trajectory-Level Evaluation of LLM Tool Calling for Long-Horizon Financial Tasks","created":"2026-04-11","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":"2601.06328","title":"C-World: A Computer Use Agent Environment Creator","created":"2026-01-09","cited_by_count":3,"area":"agents"},{"id":"2602.15945","title":"From Tool Orchestration to Code Execution: A Study of MCP Design Choices","created":"2026-02-17","cited_by_count":3,"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":"2607.05174","title":"AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments","created":"2026-07-06","cited_by_count":3,"area":"agents"},{"id":"2605.09889","title":"Skill Description Deception Attack against Task Routing in Internet of Agents","created":"2026-05-11","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":"2608.24509","title":"PeakBench: Benchmarking Resource-Aware Tool Invocation in LLM Agents","created":"2026-08-25","cited_by_count":2,"area":"agents"},{"id":"2602.18571","title":"Debug2Fix: Can Interactive Debugging Help Coding Agents Fix More Bugs?","created":"2026-02-20","cited_by_count":1,"area":"agents"},{"id":"2606.15822","title":"TrustedARI: Towards Trust-Native Agentic Routing Infrastructure for Agentic AI","created":"2026-06-14","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":"2605.29270","title":"Indexing the Unreadable: LLM-Native Recursive Construction and Search of Service Taxonomies","created":"2026-05-28","cited_by_count":0,"area":"agents"},{"id":"2606.09182","title":"Understanding How Enterprises Adopt the Model Context Protocol for LLM-Driven Software Engineering","created":"2026-06-08","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":"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":"2609.22218","title":"Toollery: Scaling LLM Agents to Thousands of Skills and Tools","created":"2026-09-02","cited_by_count":0,"area":"agents"},{"id":"2609.37025","title":"AnyAct: Universal Action for Self-Evolving Agents","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.14956","title":"MCPDisCo: Seesaw-Mitigated Tuning for MCP-Native Agents","created":"2026-10-10","cited_by_count":0,"area":"agents"}],"next_cursor":null}