{"total":67,"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":"2604.18292","title":"Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence","created":"2026-04-20","cited_by_count":54,"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":"2512.15163","title":"MCP-SafetyBench: A Benchmark for Safety Evaluation of Large Language Models with Real-World MCP Servers","created":"2025-12-17","cited_by_count":34,"area":"agents"},{"id":"2605.26684","title":"Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning","created":"2026-05-26","cited_by_count":31,"area":"agents"},{"id":"2602.03419","title":"SWE-World: Building Software Engineering Agents in Docker-Free Environments","created":"2026-02-03","cited_by_count":25,"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":"2605.06716","title":"From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms","created":"2026-05-07","cited_by_count":21,"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":"2601.04688","title":"ToolGate: Contract-Grounded and Verified Tool Execution for LLMs","created":"2026-01-08","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":"2509.26553","title":"Towards Reliable Benchmarking: A Contamination Free, Controllable Evaluation Framework for Multi-step LLM Function Calling","created":"2025-09-30","cited_by_count":13,"area":"agents"},{"id":"2511.09586","title":"Environment Scaling for Interactive Agentic Experience Collection: A Survey","created":"2025-11-12","cited_by_count":13,"area":"agents"},{"id":"2602.11224","title":"Agent-Diff: Benchmarking LLM Agents on Enterprise API Tasks via Code Execution with State-Diff-Based Evaluation","created":"2026-02-11","cited_by_count":13,"area":"agents"},{"id":"2603.24639","title":"Experiential Reflective Learning for Self-Improving LLM Agents","created":"2026-03-25","cited_by_count":13,"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":"2602.01675","title":"TRIP-Bench: A Benchmark for Long-Horizon Interactive Agents in Real-World Scenarios","created":"2026-02-02","cited_by_count":10,"area":"agents"},{"id":"2510.07307","title":"MLE-Smith: Scaling MLE Tasks with Automated Multi-Agent Pipeline","created":"2025-10-08","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":"2602.13691","title":"PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planning","created":"2026-02-14","cited_by_count":9,"area":"agents"},{"id":"2606.28480","title":"TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents","created":"2026-06-26","cited_by_count":9,"area":"agents"},{"id":"2510.16720","title":"Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AI","created":"2025-10-19","cited_by_count":8,"area":"agents"},{"id":"2606.12191","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","created":"2026-06-10","cited_by_count":8,"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":"2602.09372","title":"AgentSkiller: Scaling Generalist Agent Intelligence through Semantically Integrated Cross-Domain Data Synthesis","created":"2026-02-10","cited_by_count":6,"area":"agents"},{"id":"2603.05553","title":"EigenData: A Self-Evolving Multi-Agent Platform for Function-Calling Data Synthesis, Auditing, and Repair","created":"2026-03-05","cited_by_count":6,"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":"2604.00073","title":"Terminal Agents Suffice for Enterprise Automation","created":"2026-03-31","cited_by_count":6,"area":"agents"},{"id":"2602.07359","title":"W&D:Scaling Parallel Tool Calling for Efficient Deep Research Agents","created":"2026-02-07","cited_by_count":5,"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":"2510.19286","title":"TheMCPCompany: Creating General-purpose Agents with Task-specific Tools","created":"2025-10-22","cited_by_count":4,"area":"agents"},{"id":"2604.01532","title":"PHMForge: Evaluating LLM Agents on Industrial Prognostics through MCP-Native, Algorithm-Grounded Tools","created":"2026-04-02","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":"2601.06328","title":"C-World: A Computer Use Agent Environment Creator","created":"2026-01-09","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":"2608.21156","title":"Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence","created":"2026-08-21","cited_by_count":3,"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":"2609.05837","title":"AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories","created":"2026-09-05","cited_by_count":2,"area":"agents"},{"id":"2602.18764","title":"The Convergence of Schema-Guided Dialogue Systems and the Model Context Protocol","created":"2026-02-21","cited_by_count":1,"area":"agents"},{"id":"2603.13327","title":"DOVA: Deliberation-First Multi-Agent Orchestration for Autonomous Research Automation","created":"2026-03-04","cited_by_count":1,"area":"agents"},{"id":"2604.12162","title":"AlphaEval: Evaluating Agents in Production","created":"2026-04-14","cited_by_count":1,"area":"agents"},{"id":"2605.29676","title":"Notation Matters: A Benchmark Study of Token-Optimized Formats in Agentic AI Systems","created":"2026-05-28","cited_by_count":1,"area":"agents"},{"id":"2606.19704","title":"Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents","created":"2026-06-18","cited_by_count":1,"area":"agents"},{"id":"2608.02358","title":"ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step","created":"2026-08-03","cited_by_count":1,"area":"agents"},{"id":"2608.20314","title":"MidTool: Mid-training Data Synthesis for Agentic Tool Use","created":"2026-08-20","cited_by_count":1,"area":"agents"},{"id":"2608.22167","title":"MCP-Universe RL: A Framework for Training MCP Tool-Use Agents via Reinforcement Learning","created":"2026-08-23","cited_by_count":1,"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":"2607.11126","title":"ToolAtlas: Learning Once, Reusing Everywhere with Tool-Side Memory","created":"2026-07-13","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":"2607.22563","title":"Synthetic Scenario Generation for Evaluation of Industry 4.0 Agents","created":"2026-05-29","cited_by_count":0,"area":"agents"},{"id":"2608.24017","title":"WebMCP-Phalanx: Enforcing and Characterizing Trust Boundaries for Browser-Integrated LLM Agents","created":"2026-08-25","cited_by_count":0,"area":"agents"},{"id":"2609.23142","title":"CraftBench-UE: Deterministic Evaluation for Coding Agents in Unreal Engine","created":"2026-09-19","cited_by_count":0,"area":"agents"},{"id":"2609.24161","title":"MCP-GRANITE Benchmark: GRANularity Interface TEsting for MCP-Based LLM Agents","created":"2026-09-21","cited_by_count":0,"area":"agents"},{"id":"2610.04375","title":"Do Tool Calls Execute as Intended? Measuring and Repairing Intent-Execution Correspondence in LLM Agents","created":"2026-10-03","cited_by_count":0,"area":"agents"},{"id":"2610.04378","title":"COPEX: Benchmarking LLM Robustness to Adversarial Context Across Model Context Protocol Layers","created":"2026-10-03","cited_by_count":0,"area":"agents"},{"id":"2610.14334","title":"Which Metadata Matters for LLM Tool Selection in MCP? Evidence from Controlled Factor-Level Interventions","created":"2026-10-09","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"},{"id":"2610.14960","title":"Humans vs. Machines: A Comparison With AI Agents in Software Reverse Engineering","created":"2026-10-10","cited_by_count":0,"area":"agents"},{"id":"2610.14966","title":"SkillHorizon: Constructing Long-Horizon Agent Tasks through Skill Composition","created":"2026-10-10","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}