{"total":23,"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":"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":"2603.00718","title":"SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?","created":"2026-02-28","cited_by_count":30,"area":"agents"},{"id":"2603.11076","title":"DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use","created":"2026-03-10","cited_by_count":13,"area":"agents"},{"id":"2607.00692","title":"Self-GC: Self-Governing Context for Long-Horizon LLM Agents","created":"2026-07-01","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":"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":"2605.15104","title":"From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents","created":"2026-05-14","cited_by_count":5,"area":"agents"},{"id":"2603.23638","title":"Can LLM Agents Be CFOs? Benchmarking Long-Horizon Resource Allocation in an Uncertain Enterprise Environment","created":"2026-03-24","cited_by_count":4,"area":"agents"},{"id":"2601.09393","title":"AI-NativeBench: An Open-Source White-Box Agentic Benchmark Suite for AI-Native Systems","created":"2026-01-14","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":"2604.07551","title":"MCP-DPT: A Defense-Placement Taxonomy and Coverage Analysis for Model Context Protocol Security","created":"2026-04-08","cited_by_count":2,"area":"agents"},{"id":"2608.26623","title":"AgentJudgeBench: A Multi-Difficulty Benchmark for Evaluating LLM Judges on Agentic Tool-Calling","created":"2026-08-27","cited_by_count":2,"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":"2605.14312","title":"Making OpenAPI Documentation Agent-Ready: Detecting Documentation and REST Smells with a Multi-Agent LLM System","created":"2026-05-14","cited_by_count":0,"area":"agents"},{"id":"2605.22366","title":"AgroTools: A Benchmark for Tool-Augmented Multimodal Agents in Agriculture","created":"2026-05-21","cited_by_count":0,"area":"agents"},{"id":"2606.19795","title":"Agentic Electronic Design Automation: A Handoff Perspective","created":"2026-06-18","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":"2608.26133","title":"Agent Seer: Synthesizing Scenarios from Specification Understanding","created":"2026-06-24","cited_by_count":0,"area":"agents"},{"id":"2609.12345","title":"ParaRecover: A Process-Level Benchmark for Error Localization and Recovery in Parallel Tool-Use Agents","created":"2026-09-11","cited_by_count":0,"area":"agents"},{"id":"2610.15529","title":"Agent-Canary-Mas: End-to-End Evaluation of Protocol Risk in Long-Horizon Multi-Agent Systems","created":"2026-10-11","cited_by_count":0,"area":"agents"}],"next_cursor":null}