{"total":76,"rows":[{"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":"2605.10912","title":"WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation","created":"2026-05-11","cited_by_count":37,"area":"agents"},{"id":"2511.02734","title":"CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents","created":"2025-11-04","cited_by_count":33,"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":"2509.17158","title":"ARE: Scaling Up Agent Environments and Evaluations","created":"2025-09-21","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":"2605.02240","title":"PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments","created":"2026-05-04","cited_by_count":21,"area":"agents"},{"id":"2601.17549","title":"Breaking the Protocol: Security Analysis of the Model Context Protocol Specification and Prompt Injection Vulnerabilities in Tool-Integrated LLM Agents","created":"2026-01-24","cited_by_count":19,"area":"agents"},{"id":"2604.23781","title":"ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents","created":"2026-04-26","cited_by_count":17,"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":"2605.30785","title":"Learning Agent-Compatible Context Management for Long-Horizon Tasks","created":"2026-05-29","cited_by_count":15,"area":"agents"},{"id":"2603.22862","title":"The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration","created":"2026-03-24","cited_by_count":14,"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":"2603.11076","title":"DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use","created":"2026-03-10","cited_by_count":13,"area":"agents"},{"id":"2604.28139","title":"Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows","created":"2026-04-30","cited_by_count":13,"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":"2512.06914","title":"SoK: Trust-Authorization Mismatch in LLM Agent Interactions","created":"2025-12-07","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":"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":"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":"2602.03255","title":"LPS-Bench: Benchmarking Safety Awareness of Computer-Use Agents in Long-Horizon Planning under Benign and Adversarial Scenarios","created":"2026-02-03","cited_by_count":9,"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":"2604.10866","title":"OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation","created":"2026-04-13","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":"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":"2603.06713","title":"Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces","created":"2026-03-05","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":"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":"2605.18548","title":"STT-Arena: A More Realistic Environment for Tool-Using with Spatio-Temporal Dynamics","created":"2026-05-18","cited_by_count":4,"area":"agents"},{"id":"2606.16591","title":"SING: Synthetic Intention Graph for Scalable Active Tool Discovery in LLM Agents","created":"2026-06-15","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":"2510.00229","title":"AgentFlux: Decoupled Fine-Tuning & Inference for On-Device Agentic Systems","created":"2025-09-30","cited_by_count":3,"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":"2511.21686","title":"Matrix: Peer-to-Peer Multi-Agent Synthetic Data Generation Framework","created":"2025-11-26","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":"2602.15945","title":"From Tool Orchestration to Code Execution: A Study of MCP Design Choices","created":"2026-02-17","cited_by_count":3,"area":"agents"},{"id":"2604.00131","title":"Oblivion: Self-Adaptive Agentic Memory Control through Decay-Driven Activation","created":"2026-03-31","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":"2605.02168","title":"Planner Matters! An Efficient and Unbalanced Multi-agent Collaboration Framework for Long-horizon Planning","created":"2026-05-04","cited_by_count":3,"area":"agents"},{"id":"2605.19743","title":"EngiAI: Capability-Based Evaluation of Tool-Connected LLM Agents for Engineering Design","created":"2026-05-19","cited_by_count":3,"area":"agents"},{"id":"2606.12908","title":"SENTINEL: Failure-Driven Reinforcement Learning for Training Tool-Using Language Model Agents","created":"2026-06-11","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":"2608.11386","title":"The Devil Is in the Interface: Evaluating How Tool Architecture Shapes Coding Agent Behavior","created":"2026-08-11","cited_by_count":3,"area":"agents"},{"id":"2608.19741","title":"One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows","created":"2026-08-20","cited_by_count":3,"area":"agents"},{"id":"2608.27260","title":"What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents","created":"2026-08-27","cited_by_count":3,"area":"agents"},{"id":"2603.28428","title":"Synergy: A Next-Generation General-Purpose Agent for Open Agentic Web","created":"2026-03-30","cited_by_count":2,"area":"agents"},{"id":"2606.10209","title":"Less Context, Better Agents: Efficient Context Engineering for Long-Horizon Tool-Using LLM Agents","created":"2026-06-08","cited_by_count":2,"area":"agents"},{"id":"2606.12674","title":"Evoflux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents","created":"2026-06-10","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":"2608.24509","title":"PeakBench: Benchmarking Resource-Aware Tool Invocation in LLM Agents","created":"2026-08-25","cited_by_count":2,"area":"agents"},{"id":"2601.08196","title":"Evaluating Implicit Regulatory Compliance in LLM Tool Invocation via Logic-Guided Synthesis","created":"2026-01-13","cited_by_count":1,"area":"agents"},{"id":"2604.25914","title":"DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios","created":"2026-04-28","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":"2607.23933","title":"SpecBox: Speculative Sandbox Scheduling for Efficient LLM Agent Serving","created":"2026-07-27","cited_by_count":1,"area":"agents"},{"id":"2511.08487","title":"How Brittle is Agent Safety? Rethinking Agent Risk under Intent Concealment and Task Complexity","created":"2025-11-11","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":"2605.14051","title":"SPIN: Structural LLM Planning via Iterative Navigation for Industrial Tasks","created":"2026-05-13","cited_by_count":0,"area":"agents"},{"id":"2605.17774","title":"Internalizing Tool Knowledge in Small Language Models via QLoRA Fine-Tuning","created":"2026-05-18","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":"2607.22563","title":"Synthetic Scenario Generation for Evaluation of Industry 4.0 Agents","created":"2026-05-29","cited_by_count":0,"area":"agents"},{"id":"2608.20481","title":"AEGIS: Preventing Cross-Domain Resource Abuse in MCP","created":"2026-08-20","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":"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":"2609.08404","title":"Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks","created":"2026-09-08","cited_by_count":0,"area":"agents"},{"id":"2610.03591","title":"HazardWeaver: Scientific Route Selection for Hazard Analysis Agents","created":"2026-10-02","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":"2610.04973","title":"TrajLong: Co-Designing Agentic and Long-Context Supervision for Mid-Training","created":"2026-10-04","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":"2610.14966","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}