{"total":101,"rows":[{"id":"2507.13334","title":"A Survey of Context Engineering for Large Language Models","created":"2025-07-17","cited_by_count":126,"area":null},{"id":"2604.08224","title":"Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering","created":"2026-04-09","cited_by_count":74,"area":"agents"},{"id":"2506.23260","title":"From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflows","created":"2025-06-29","cited_by_count":58,"area":"agents"},{"id":"2506.19676","title":"A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures","created":"2025-06-24","cited_by_count":57,"area":"agents"},{"id":"2509.18970","title":"LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions","created":"2025-09-23","cited_by_count":50,"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":"2506.12508","title":"AgentOrchestra: Orchestrating Multi-Agent Intelligence with the Tool-Environment-Agent(TEA) Protocol","created":"2025-06-14","cited_by_count":39,"area":"agents"},{"id":"2510.24563","title":"OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents","created":"2025-10-28","cited_by_count":29,"area":"lr"},{"id":"2505.19301","title":"A Novel Zero-Trust Identity Framework for Agentic AI: Decentralized Authentication and Fine-Grained Access Control","created":"2025-05-25","cited_by_count":28,"area":"agents"},{"id":"2506.13666","title":"We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems","created":"2025-06-16","cited_by_count":27,"area":"agents"},{"id":"2508.17692","title":"LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios","created":"2025-08-25","cited_by_count":26,"area":"lr"},{"id":"2508.05294","title":"Towards Embodied Agentic AI: Review and Classification of LLM- and VLM-Driven Robot Autonomy and Interaction","created":"2025-08-07","cited_by_count":19,"area":"mllm"},{"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":"2508.10146","title":"Agentic AI Frameworks: Architectures, Protocols, and Design Challenges","created":"2025-08-13","cited_by_count":16,"area":"agents"},{"id":"2512.08290","title":"Systematization of Knowledge: Security and Safety in the Model Context Protocol Ecosystem","created":"2025-12-09","cited_by_count":16,"area":"agents"},{"id":"2602.11327","title":"Security Threat Modeling for Emerging AI-Agent Protocols: A Comparative Analysis of MCP, A2A, Agora, and ANP","created":"2026-02-11","cited_by_count":15,"area":"agents"},{"id":"2512.01939","title":"An Empirical Study of Agent Developer Practices in AI Agent Frameworks","created":"2025-12-01","cited_by_count":14,"area":"agents"},{"id":"2601.10955","title":"Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agents","created":"2026-01-16","cited_by_count":14,"area":"agents"},{"id":"2507.21105","title":"AgentMaster: A Multi-Agent Conversational Framework Using A2A and MCP Protocols for Multimodal Information Retrieval and Analysis","created":"2025-07-08","cited_by_count":13,"area":"agents"},{"id":"2509.25292","title":"A Measurement Study of Model Context Protocol Ecosystem","created":"2025-09-29","cited_by_count":13,"area":"agents"},{"id":"2511.02687","title":"The Collaboration Gap: Exploration and Benchmarking of Open-World Agentic Cooperation","created":"2025-11-04","cited_by_count":13,"area":"agents"},{"id":"2601.04583","title":"Autonomous Agents on Blockchains: Standards, Execution Models, and Trust Boundaries","created":"2026-01-08","cited_by_count":13,"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":"2512.10169","title":"The 2025 Foundation Model Transparency Index","created":"2025-12-11","cited_by_count":11,"area":null},{"id":"2606.17546","title":"SEAGym: An Evaluation Environment for Self-Evolving LLM Agents","created":"2026-06-16","cited_by_count":11,"area":"agents"},{"id":"2505.09757","title":"Trustless Autonomy: Understanding Motivations, Benefits, and Governance Dilemmas in Self-Sovereign Decentralized AI Agents","created":"2025-05-14","cited_by_count":10,"area":"agents"},{"id":"2511.03841","title":"Security Analysis of Agentic AI Communication Protocols: A Comparative Evaluation","created":"2025-11-05","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":"2505.21550","title":"Position: Collaborative Agentic AI Needs Interoperability Across Ecosystems","created":"2025-05-25","cited_by_count":8,"area":"agents"},{"id":"2507.06323","title":"Bridging AI and Software Security: A Comparative Vulnerability Assessment of LLM Agent Deployment Paradigms","created":"2025-07-08","cited_by_count":7,"area":"agents"},{"id":"2507.10644","title":"From Multi-Agent Systems and the Semantic Web to Agentic AI: A Unified Narrative of the Web of Agents","created":"2025-07-14","cited_by_count":7,"area":"agents"},{"id":"2505.13523","title":"ACPs: Agent Collaboration Protocols for the Internet of Agents","created":"2025-05-18","cited_by_count":6,"area":null},{"id":"2506.04565","title":"From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2508.01012","title":"AutoEDA: Enabling EDA Flow Automation through Microservice-Based LLM Agents","created":"2025-08-01","cited_by_count":6,"area":"agents"},{"id":"2509.24380","title":"Agentic Services Computing","created":"2025-09-29","cited_by_count":6,"area":"agents"},{"id":"2510.17149","title":"ProtocolBench: Which LLM MultiAgent Protocol to Choose?","created":"2025-10-20","cited_by_count":6,"area":null},{"id":"2511.11332","title":"UFO3: Weaving the Digital Agent Galaxy","created":"2025-11-14","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":"2605.14892","title":"Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems","created":"2026-05-14","cited_by_count":6,"area":"agents"},{"id":"2506.13800","title":"Enhancing Clinical Decision Support and EHR Insights through LLMs and the Model Context Protocol: An Open-Source MCP-FHIR Framework","created":"2025-06-13","cited_by_count":5,"area":null},{"id":"2507.10593","title":"ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMs","created":"2025-07-11","cited_by_count":5,"area":"agents"},{"id":"2508.03095","title":"Evolution of AI Agent Registry Solutions: Centralized, Enterprise, and Distributed Approaches","created":"2025-08-05","cited_by_count":4,"area":null},{"id":"2510.02567","title":"Agentic Additive Manufacturing Alloy Evaluation","created":"2025-10-02","cited_by_count":4,"area":"agents"},{"id":"2605.30169","title":"Dissociative Identity: Language Model Agents Lack Grounding for Reputation Mechanisms","created":"2026-05-28","cited_by_count":4,"area":"agents"},{"id":"2608.07556","title":"MasDrift: Benchmarking Authorization Preservation Across Multi-Agent Architectures","created":"2026-08-02","cited_by_count":4,"area":null},{"id":"2507.07901","title":"The Trust Fabric: Decentralized Interoperability and Economic Coordination for the Agentic Web","created":"2025-07-10","cited_by_count":3,"area":"agents"},{"id":"2508.02979","title":"Unified Tool Integration for LLMs: A Protocol-Agnostic Approach to Function Calling","created":"2025-08-05","cited_by_count":3,"area":"agents"},{"id":"2602.07652","title":"Agent-Fence: Mapping Security Vulnerabilities Across Deep Research Agents","created":"2026-02-07","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":"2602.20493","title":"AWCP: A Workspace Delegation Protocol for Deep-Engagement Collaboration across Remote Agents","created":"2026-02-24","cited_by_count":3,"area":"agents"},{"id":"2604.05969","title":"A Formal Security Framework for MCP-Based AI Agents: Threat Taxonomy, Verification Models, and Defense Mechanisms","created":"2026-04-07","cited_by_count":3,"area":"agents"},{"id":"2505.22311","title":"From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communications","created":"2025-05-28","cited_by_count":2,"area":"agents"},{"id":"2506.02739","title":"Why do AI agents communicate in human language?","created":"2025-06-03","cited_by_count":2,"area":"agents"},{"id":"2506.12312","title":"Perspective on Utilizing Foundation Models for Laboratory Automation in Materials Research","created":"2025-06-14","cited_by_count":2,"area":null},{"id":"2510.16572","title":"Ripple Effect Protocol: Coordinating Agent Populations","created":"2025-10-18","cited_by_count":2,"area":"agents"},{"id":"2604.02369","title":"Beyond Message Passing: A Semantic View of Agent Communication Protocols","created":"2026-03-30","cited_by_count":2,"area":"agents"},{"id":"2604.09744","title":"MPAC: A Multi-Principal Agent Coordination Protocol for Interoperable Multi-Agent Collaboration","created":"2026-04-10","cited_by_count":2,"area":"agents"},{"id":"2604.24477","title":"GAMMAF: A Common Framework for Graph-Based Anomaly Monitoring Benchmarking in LLM Multi-Agent Systems","created":"2026-04-27","cited_by_count":2,"area":"agents"},{"id":"2605.02489","title":"GRAIL: A Deep-Granularity Hybrid Resonance Framework for Real-Time Agent Discovery via SLM-Enhanced Indexing","created":"2026-05-04","cited_by_count":2,"area":"agents"},{"id":"2606.00288","title":"Model-Native Computing Architecture: Envisioning Future System Architecture Through the Lens of Computer Architecture","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2606.03755","title":"LAP: An Agent-to-Instrument Protocol for Autonomous Science","created":"2026-06-02","cited_by_count":2,"area":"agents"},{"id":"2607.11175","title":"The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomy","created":"2026-07-13","cited_by_count":2,"area":"mllm"},{"id":"2608.17597","title":"HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety","created":"2026-08-18","cited_by_count":2,"area":"agents"},{"id":"2505.19339","title":"Towards Humanoid Robot Autonomy: A Dynamic Architecture Integrating Continuous thought Machines (CTM) and Model Context Protocol (MCP)","created":"2025-05-25","cited_by_count":1,"area":"agents"},{"id":"2508.19239","title":"Model Context Protocols in Adaptive Transport Systems: A Survey","created":"2025-08-26","cited_by_count":1,"area":"agents"},{"id":"2509.04979","title":"Internet 3.0: Architecture for a Web-of-Agents with it's Algorithm for Ranking Agents","created":"2025-09-05","cited_by_count":1,"area":"lr"},{"id":"2510.15842","title":"Paper2Web: Let's Make Your Paper Alive!","created":"2025-10-17","cited_by_count":1,"area":null},{"id":"2601.05016","title":"From Idea to Co-Creation: A Planner-Actor-Critic Framework for Agent Augmented 3D Modeling","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2603.03753","title":"Agentic Peer-to-Peer Networks: From Content Distribution to Capability and Action Sharing","created":"2026-03-04","cited_by_count":1,"area":"agents"},{"id":"2603.22823","title":"Empirical Comparison of Agent Communication Protocols for Task Orchestration","created":"2026-03-24","cited_by_count":1,"area":"agents"},{"id":"2604.17950","title":"CADMAS-CTX: Contextual Capability Calibration for Multi-Agent Delegation","created":"2026-04-20","cited_by_count":1,"area":"agents"},{"id":"2604.19540","title":"Mesh Memory Protocol: Semantic Infrastructure for Multi-Agent LLM Systems","created":"2026-04-21","cited_by_count":1,"area":"agents"},{"id":"2605.22733","title":"HarnessAPI: A Skill-First Framework for Unified Streaming APIs and MCP Tools","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2605.25815","title":"Behind EvoMap: Characterizing a Self-Evolving Agent-to-Agent Collaboration Network","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2606.07150","title":"From Privacy to Workflow Integrity: Communication-Graph Metadata in Autonomous Agent Interoperability","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2606.19135","title":"A Technical Taxonomy of LLM Agent Communication Protocols","created":"2026-06-17","cited_by_count":1,"area":"agents"},{"id":"2608.04626","title":"Blockchain Empowered Trustworthy Agent Networks: Foundations, Taxonomy, and Future Directions","created":"2026-08-05","cited_by_count":1,"area":"agents"},{"id":"2608.27184","title":"LLMs in Digital EDA: A perspective on shifting roles from Generation to Orchestration","created":"2026-08-27","cited_by_count":1,"area":null},{"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":"2509.12592","title":"Match Chat: Real Time Generative AI and Generative Computing for Tennis","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2509.14289","title":"From Capabilities to Performance: Evaluating Key Functional Properties of LLM Architectures in Penetration Testing","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2510.08263","title":"Co-TAP: Three-Layer Agent Interaction Protocol Technical Report","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2510.21566","title":"ColorEcosystem: Powering Personalized, Standardized, and Trustworthy Agentic Service in massive-agent Ecosystem","created":"2025-10-24","cited_by_count":0,"area":"agents"},{"id":"2511.18715","title":"HuggingR$^{4}$: A Progressive Reasoning Framework for Discovering Optimal Model Companions","created":"2025-11-24","cited_by_count":0,"area":"lr"},{"id":"2512.20649","title":"AIAuditTrack: A Framework for AI Security system","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2602.11754","title":"Cooperation Breakdown in LLM Agents Under Communication Delays","created":"2026-02-12","cited_by_count":0,"area":"agents"},{"id":"2603.22359","title":"STEM Agent: A Self-Adapting, Tool-Enabled, Extensible Architecture for Multi-Protocol AI Agent Systems","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2605.28148","title":"DeltaMCP: Incremental Regeneration via Spec-Aware Transformation for MCP servers","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.19795","title":"Agentic Electronic Design Automation: A Handoff Perspective","created":"2026-06-18","cited_by_count":0,"area":"agents"},{"id":"2606.30246","title":"Clarus: Coordinating Autonomous Research Agents toward Web-Scale Scientific Collaboration","created":"2026-06-29","cited_by_count":0,"area":"agents"},{"id":"2607.04219","title":"Agentic IoT: Architectures, Applications, and Challenges Toward the Internet of Agents","created":"2026-07-05","cited_by_count":0,"area":"agents"},{"id":"2607.09678","title":"Faithful, Not Corrective: Model Capability Governs Message-Format Effects in Multi-Hop Agent Relays","created":"2026-06-12","cited_by_count":0,"area":"agents"},{"id":"2607.18242","title":"AI Tool Discovery at Scale: All You Need is DNS","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2607.23884","title":"A Comparative Study of MCP and A2A for Inter-Agent Coordination in LLM-Based Systems","created":"2026-07-26","cited_by_count":0,"area":"agents"},{"id":"2608.04292","title":"Binding Biometrics with AI Agent Identifiers for Delegation of Authority","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.08467","title":"LLM within MCP Matters: Measuring Inefficient Resource Utilization Driven by LLMs","created":"2026-08-09","cited_by_count":0,"area":"agents"},{"id":"2608.28553","title":"Composition without a Host: Carrying the Spatiotemporal-Composability Guarantee of Plugin-Based Agents across Processes","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2608.29483","title":"GeoAgent: Evaluating VLM Geolocalization Through Embodied Navigation","created":"2026-08-30","cited_by_count":0,"area":"mllm"},{"id":"2609.20095","title":"A Scalable Trust Discovery Architecture for the Internet of Agents","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.13703","title":"A Baseline Assessment for the Agentic Web Technology Stack","created":"2026-10-09","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}