{"total":31,"rows":[{"id":"2401.05566","title":"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training","created":"2024-01-10","cited_by_count":529,"area":"agents"},{"id":"2404.11584","title":"The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey","created":"2024-04-17","cited_by_count":168,"area":"agents"},{"id":"2402.07510","title":"Secret Collusion among AI Agents: Multi-Agent Deception via Steganography","created":"2024-02-12","cited_by_count":113,"area":"agents"},{"id":"2503.03750","title":"The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems","created":"2025-03-05","cited_by_count":72,"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":"2411.05990","title":"Game-theoretic LLM: Agent Workflow for Negotiation Games","created":"2024-11-08","cited_by_count":56,"area":"agents"},{"id":"2509.10723","title":"Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight","created":"2025-09-12","cited_by_count":16,"area":"agents"},{"id":"2504.03255","title":"Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective","created":"2025-04-04","cited_by_count":13,"area":"agents"},{"id":"2512.20798","title":"A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents","created":"2025-12-23","cited_by_count":13,"area":"agents"},{"id":"2410.09114","title":"Catastrophic Cyber Capabilities Benchmark (3CB): Robustly Evaluating LLM Agent Cyber Offense Capabilities","created":"2024-10-10","cited_by_count":12,"area":"agents"},{"id":"2506.07388","title":"Shapley-Coop: Credit Assignment for Emergent Cooperation in Self-Interested LLM Agents","created":"2025-06-09","cited_by_count":12,"area":"agents"},{"id":"2604.01151","title":"Detecting Multi-Agent Collusion Through Multi-Agent Interpretability","created":"2026-04-01","cited_by_count":7,"area":"agents"},{"id":"2504.13707","title":"OpenDeception: Learning Deception and Trust in Human-AI Interaction via Multi-Agent Simulation","created":"2025-04-18","cited_by_count":5,"area":"agents"},{"id":"2605.00073","title":"AgentReputation: A Decentralized Agentic AI Reputation Framework","created":"2026-04-30","cited_by_count":4,"area":"agents"},{"id":"2504.03726","title":"Detecting Malicious AI Agents Through Simulated Interactions","created":"2025-03-31","cited_by_count":2,"area":"agents"},{"id":"2510.23245","title":"Multi-Stakeholder Alignment in LLM-Powered Collaborative AI Systems: A Multi-Agent Framework for Intelligent Tutoring","created":"2025-10-27","cited_by_count":2,"area":"agents"},{"id":"2604.04561","title":"Mapping the Exploitation Surface: A 10,000-Trial Taxonomy of What Makes LLM Agents Exploit Vulnerabilities","created":"2026-04-06","cited_by_count":2,"area":"agents"},{"id":"2605.10059","title":"Strategic Exploitation in LLM Agent Markets: A Simulation Framework for E-Commerce Trust","created":"2026-05-11","cited_by_count":2,"area":"agents"},{"id":"2608.26372","title":"Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives","created":"2026-08-26","cited_by_count":2,"area":"agents"},{"id":"2602.04197","title":"From Helpfulness to Toxic Proactivity: Diagnosing Behavioral Misalignment in LLM Agents","created":"2026-02-04","cited_by_count":1,"area":"agents"},{"id":"2602.05183","title":"Data-Centric Interpretability for LLM-based Multi-Agent Reinforcement Learning","created":"2026-02-05","cited_by_count":1,"area":"agents"},{"id":"2603.07202","title":"Lying to Win: Assessing LLM Deception through Human-AI Games and Parallel-World Probing","created":"2026-03-07","cited_by_count":1,"area":"agents"},{"id":"2509.10875","title":"Is the `Agent' Paradigm a Limiting Framework for Next-Generation Intelligent Systems?","created":"2025-09-13","cited_by_count":0,"area":"agents"},{"id":"2602.22070","title":"Language Models Exhibit Inconsistent Biases Towards Algorithmic Agents and Human Experts","created":"2026-02-25","cited_by_count":0,"area":"agents"},{"id":"2603.14417","title":"Questionnaire Responses Do not Capture the Safety of AI Agents","created":"2026-03-15","cited_by_count":0,"area":"agents"},{"id":"2605.16436","title":"The End of Trust: How Agentic AI Breaks Security Assumptions","created":"2026-05-14","cited_by_count":0,"area":"agents"},{"id":"2606.10304","title":"MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents","created":"2026-06-09","cited_by_count":0,"area":"agents"},{"id":"2607.05132","title":"When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games","created":"2026-07-06","cited_by_count":0,"area":"agents"},{"id":"2607.06608","title":"Security and Privacy in Agentic AI: Grand Challenges and Future Directions","created":"2026-07-07","cited_by_count":0,"area":"agents"},{"id":"2607.14285","title":"ToolAlignBench: Investigating Alignment Conflicts in Tool-Calling Enabled LLMs","created":"2026-07-15","cited_by_count":0,"area":"agents"},{"id":"2609.13731","title":"Trustworthy Agentic AI: A Comprehensive Cybersecurity and Systems Survey on Threat Landscapes, Defense Architectures, and Open Challenges","created":"2026-09-12","cited_by_count":0,"area":"agents"}],"next_cursor":null}