{"total":62,"rows":[{"id":"2510.23883","title":"Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges","created":"2025-10-27","cited_by_count":28,"area":"agents"},{"id":"2601.05293","title":"A Survey of Agentic AI and Cybersecurity: Challenges, Opportunities and Use-case Prototypes","created":"2026-01-08","cited_by_count":22,"area":"agents"},{"id":"2602.15198","title":"Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems","created":"2026-02-16","cited_by_count":18,"area":"agents"},{"id":"2512.04864","title":"Are Your Agents Upward Deceivers?","created":"2025-12-04","cited_by_count":16,"area":"agents"},{"id":"2511.06626","title":"Spilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectives","created":"2025-11-10","cited_by_count":15,"area":"agents"},{"id":"2602.08235","title":"When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents","created":"2026-02-09","cited_by_count":14,"area":"agents"},{"id":"2603.01608","title":"Evaluating and Understanding Scheming Propensity in LLM Agents","created":"2026-03-02","cited_by_count":14,"area":"agents"},{"id":"2604.16968","title":"On Safety Risks in Experience-Driven Self-Evolving Agents","created":"2026-04-18","cited_by_count":14,"area":"agents"},{"id":"2602.08995","title":"When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents","created":"2026-02-09","cited_by_count":8,"area":"agents"},{"id":"2606.16613","title":"CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent Economies","created":"2026-06-15","cited_by_count":8,"area":"agents"},{"id":"2512.07497","title":"How Do LLMs Fail In Agentic Scenarios? A Qualitative Analysis of Success and Failure Scenarios of Various LLMs in Agentic Simulations","created":"2025-12-08","cited_by_count":7,"area":"agents"},{"id":"2601.08118","title":"MirrorBench: A Benchmark to Evaluate Conversational User-Proxy Agents for Human-Likeness","created":"2026-01-13","cited_by_count":7,"area":"agents"},{"id":"2602.13855","title":"From Fluent to Verifiable: Claim-Level Auditability for Deep Research Agents","created":"2026-02-14","cited_by_count":7,"area":"agents"},{"id":"2603.23802","title":"How are AI agents used? Evidence from 177,000 MCP tools","created":"2026-03-25","cited_by_count":7,"area":"agents"},{"id":"2510.05192","title":"From surveillance to signalling: escalation channels as environmental controls for agentic AI","created":"2025-10-06","cited_by_count":6,"area":"agents"},{"id":"2602.22303","title":"Training Agents to Self-Report Misbehavior","created":"2026-02-25","cited_by_count":6,"area":"agents"},{"id":"2607.01236","title":"Safeguarding LLM Agents from Misalignment through Provenance Analysis","created":"2026-05-01","cited_by_count":6,"area":"agents"},{"id":"2601.12822","title":"MirrorGuard: Toward Secure Computer-Use Agents via Simulation-to-Real Reasoning Correction","created":"2026-01-19","cited_by_count":5,"area":"agents"},{"id":"2603.06874","title":"LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models","created":"2026-03-06","cited_by_count":5,"area":"agents"},{"id":"2604.15559","title":"Subliminal Transfer of Unsafe Behaviors in AI Agent Distillation","created":"2026-04-16","cited_by_count":5,"area":"agents"},{"id":"2606.28425","title":"Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems","created":"2026-06-25","cited_by_count":5,"area":"agents"},{"id":"2603.03456","title":"Asymmetric Goal Drift in Coding Agents Under Value Conflict","created":"2026-03-03","cited_by_count":4,"area":"agents"},{"id":"2605.30322","title":"Gram: Assessing sabotage propensities via automated alignment auditing","created":"2026-05-28","cited_by_count":4,"area":"agents"},{"id":"2606.05647","title":"Coding with \"Enemy\": Can Human Developers Detect AI Agent Sabotage?","created":"2026-06-04","cited_by_count":4,"area":"agents"},{"id":"2601.23211","title":"Multi-Agent Systems Should be Treated as Principal-Agent Problems","created":"2026-01-30","cited_by_count":3,"area":"agents"},{"id":"2602.00755","title":"Evolving Interpretable Constitutions for Multi-Agent Coordination","created":"2026-01-31","cited_by_count":3,"area":"agents"},{"id":"2605.06490","title":"Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors","created":"2026-05-07","cited_by_count":3,"area":"agents"},{"id":"2603.14975","title":"Why Agents Compromise Safety Under Pressure","created":"2026-03-16","cited_by_count":2,"area":"agents"},{"id":"2604.15236","title":"Agentic Microphysics: A Manifesto for Generative AI Safety","created":"2026-04-16","cited_by_count":2,"area":"agents"},{"id":"2605.08460","title":"When Child Inherits: Modeling and Exploiting Subagent Spawn in Multi-Agent Networks","created":"2026-05-08","cited_by_count":2,"area":"agents"},{"id":"2606.30449","title":"Internal-State Probes Read the Situation, Not the Action: Three Negative Results for Pre-Action Misalignment Monitoring","created":"2026-06-29","cited_by_count":2,"area":"agents"},{"id":"2607.10750","title":"Filtering Harmful Actions Isn't Enough: Phantom Transfer in Agentic SDF","created":"2026-07-12","cited_by_count":2,"area":"agents"},{"id":"2607.15434","title":"Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation","created":"2026-07-16","cited_by_count":2,"area":"agents"},{"id":"2608.14825","title":"Emergent Misaligned Communication in Long-Horizon Multi-Agent LLM Commerce","created":"2026-08-14","cited_by_count":2,"area":"agents"},{"id":"2510.21524","title":"EU-Agent-Bench: Measuring Illegal Behavior of LLM Agents Under EU Law","created":"2025-10-24","cited_by_count":1,"area":"agents"},{"id":"2601.17344","title":"The Shadow Self: Intrinsic Value Misalignment in Large Language Model Agents","created":"2026-01-24","cited_by_count":1,"area":"agents"},{"id":"2604.02500","title":"I must delete the evidence: AI Agents Explicitly Cover up Fraud and Violent Crime","created":"2026-04-02","cited_by_count":1,"area":"agents"},{"id":"2604.17502","title":"Towards Shutdownable Agents: Generalizing Stochastic Choice in RL Agents and LLMs","created":"2026-04-19","cited_by_count":1,"area":"agents"},{"id":"2604.23646","title":"Structural Enforcement of Goal Integrity in AI Agents via Separation-of-Powers Architecture","created":"2026-04-26","cited_by_count":1,"area":"agents"},{"id":"2605.22842","title":"The Misattribution Gap: When Memory Poisoning Looks Like Model Failure in Agentic AI Systems","created":"2026-05-12","cited_by_count":1,"area":"agents"},{"id":"2605.24197","title":"A Sober Look at Agentic Misalignment in Automated Workflows","created":"2026-05-22","cited_by_count":1,"area":"agents"},{"id":"2606.09692","title":"Observability for Delegated Execution in Agentic AI Systems","created":"2026-06-08","cited_by_count":1,"area":"agents"},{"id":"2609.39050","title":"Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems","created":"2026-09-30","cited_by_count":1,"area":"agents"},{"id":"2603.05028","title":"Survive at All Costs: Exploring LLM's Risky Behaviors under Survival Pressure","created":"2026-03-05","cited_by_count":0,"area":"agents"},{"id":"2603.07848","title":"Intentional Deception as Controllable Capability in LLM Agents","created":"2026-03-08","cited_by_count":0,"area":"agents"},{"id":"2603.13244","title":"Agentic AI, Retrieval-Augmented Generation, and the Institutional Turn: Legal Architectures and Financial Governance in the Age of Distributional AGI","created":"2026-02-20","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":"2606.28456","title":"Is Lying an Emergent Behaviour in LLMs? Evidence from Gaslighting AI agents in a Sustainability Game","created":"2026-06-26","cited_by_count":0,"area":"agents"},{"id":"2606.31046","title":"OpenLife: Toward Open-World Artificial Life with Autonomous LLM Agents","created":"2026-06-30","cited_by_count":0,"area":"agents"},{"id":"2608.09857","title":"Agentic Harnesses: LLM-Driven Verification Layers for Robot Autonomy","created":"2026-08-10","cited_by_count":0,"area":"agents"},{"id":"2608.15304","title":"Understanding Cognition-Induced Risks in Agentic AI Systems","created":"2026-08-15","cited_by_count":0,"area":"agents"},{"id":"2608.20940","title":"The Logic of Machine Self-Preservation","created":"2026-08-21","cited_by_count":0,"area":"agents"},{"id":"2608.27348","title":"INTENT-AS-A-TOOL Makes it Easy to Track Agentic Misalignment","created":"2026-08-27","cited_by_count":0,"area":"agents"},{"id":"2608.29460","title":"Can escalation channels redirect reward hacking toward defect disclosure?","created":"2026-08-29","cited_by_count":0,"area":"agents"},{"id":"2609.05036","title":"Moral Competence Before Moral Content: Why LLM Agents Lack the Prerequisites for Coherent Alignment","created":"2026-09-04","cited_by_count":0,"area":"agents"},{"id":"2609.05995","title":"Agentic Pressure: The Endogenous Entropy of Reliable Autonomy","created":"2026-09-05","cited_by_count":0,"area":"agents"},{"id":"2609.08126","title":"SchemeArena: Factorized Stress Testing of Scheming in LLM Agents","created":"2026-09-08","cited_by_count":0,"area":"agents"},{"id":"2609.17320","title":"Emergence World: Adversarial Stress-Testing of Long-Horizon Multi-Agent Systems","created":"2026-09-15","cited_by_count":0,"area":"agents"},{"id":"2609.19843","title":"A Dual-Process Perspective on Nudge Susceptibility in LLM-Based GUI Agents","created":"2026-09-17","cited_by_count":0,"area":"agents"},{"id":"2609.30137","title":"Screen Before You Serve: Simulation for Production Customer Experience AI Agents at 140M Scale","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.30266","title":"LLM Agents Can Easily Tamper With Their Own Traces","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2610.04083","title":"Self-Propagating Misalignment in LLM Agents, and Why Auditing or Disabling Memory Is Not Enough","created":"2026-10-02","cited_by_count":0,"area":"agents"}],"next_cursor":null}