{"total":81,"rows":[{"id":"2501.06322","title":"Multi-Agent Collaboration Mechanisms: A Survey of LLMs","created":"2025-01-10","cited_by_count":431,"area":"agents"},{"id":"2510.05179","title":"Agentic Misalignment: How LLMs Could Be Insider Threats","created":"2025-10-05","cited_by_count":158,"area":"agents"},{"id":"2507.06134","title":"OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety","created":"2025-07-08","cited_by_count":75,"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":"2506.15740","title":"SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents","created":"2025-06-17","cited_by_count":71,"area":"agents"},{"id":"2501.17315","title":"A sketch of an AI control safety case","created":"2025-01-28","cited_by_count":39,"area":"agents"},{"id":"2508.19461","title":"Reliable Weak-to-Strong Monitoring of LLM Agents","created":"2025-08-26","cited_by_count":31,"area":"agents"},{"id":"2505.24201","title":"SentinelAgent: Graph-based Anomaly Detection in Multi-Agent Systems","created":"2025-05-30","cited_by_count":22,"area":"agents"},{"id":"2511.20703","title":"PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic Approach","created":"2025-11-24","cited_by_count":22,"area":"agents"},{"id":"2507.14293","title":"WebGuard: Building a Generalizable Guardrail for Web Agents","created":"2025-07-18","cited_by_count":21,"area":"agents"},{"id":"2504.05259","title":"How to evaluate control measures for LLM agents? A trajectory from today to superintelligence","created":"2025-04-07","cited_by_count":20,"area":"agents"},{"id":"2601.11369","title":"Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphs","created":"2026-01-16","cited_by_count":20,"area":"agents"},{"id":"2508.05687","title":"Risk Analysis Techniques for Governed LLM-based Multi-Agent Systems","created":"2025-08-06","cited_by_count":18,"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":"2603.00829","title":"Constitutional Black-Box Monitoring for Scheming in LLM Agents","created":"2026-02-28","cited_by_count":10,"area":"agents"},{"id":"2505.20625","title":"Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaboration","created":"2025-05-27","cited_by_count":7,"area":"agents"},{"id":"2509.25302","title":"Dive into the Agent Matrix: A Realistic Evaluation of Self-Replication Risk in LLM Agents","created":"2025-09-29","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":"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":"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":"2603.15408","title":"TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systems","created":"2026-03-16","cited_by_count":5,"area":"agents"},{"id":"2607.02514","title":"Distributed Attacks in Persistent-State AI Control","created":"2026-07-02","cited_by_count":5,"area":"agents"},{"id":"2605.16282","title":"Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents","created":"2026-04-11","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":"2608.12323","title":"Why Do AI Agents Break Rules? How Framing, Context, and Social Signals Shape Compliance","created":"2026-05-29","cited_by_count":4,"area":"agents"},{"id":"2609.20812","title":"Quantifying Overclaiming Propensity in Frontier LLM Agents","created":"2026-09-17","cited_by_count":4,"area":"agents"},{"id":"2601.09393","title":"AI-NativeBench: An Open-Source White-Box Agentic Benchmark Suite for AI-Native Systems","created":"2026-01-14","cited_by_count":3,"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":"2604.03121","title":"An Independent Safety Evaluation of Kimi K2.5","created":"2026-04-03","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":"2508.15510","title":"Super-additive Cooperation in Language Model Agents","created":"2025-08-21","cited_by_count":2,"area":"agents"},{"id":"2510.01164","title":"Social Welfare Function Leaderboard: When LLM Agents Allocate Social Welfare","created":"2025-10-01","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":"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":"2608.26372","title":"Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives","created":"2026-08-26","cited_by_count":2,"area":"agents"},{"id":"2609.28614","title":"Reward Hacking Challenges Oversight of Autonomous Research Agents","created":"2026-09-23","cited_by_count":2,"area":"agents"},{"id":"2506.23689","title":"Pok\\'eAI: A Goal-Generating, Battle-Optimizing Multi-agent System for Pokemon Red","created":"2025-06-30","cited_by_count":1,"area":"agents"},{"id":"2509.22735","title":"Regulating the Agency of LLM-based Agents","created":"2025-09-25","cited_by_count":1,"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":"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":"2606.02380","title":"SPADE-Bench: Evaluating Spontaneous Strategic Deception in Agents via Plan-Action Divergence","created":"2026-06-01","cited_by_count":1,"area":"agents"},{"id":"2607.01153","title":"Adversarial Pragmatics for AI Safety Evaluation: A Diagnostic Framework and Seed Benchmark for Language-Mediated Control","created":"2026-07-01","cited_by_count":1,"area":"agents"},{"id":"2607.21518","title":"Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation","created":"2026-07-23","cited_by_count":1,"area":"agents"},{"id":"2607.22445","title":"Dynamic Capability Scoping for Enterprise AI Agents: A Synthetic Dataset and Three-Source Permission Architecture","created":"2026-07-24","cited_by_count":1,"area":"agents"},{"id":"2607.25076","title":"Towards an Agent Operating System - Lessons from Classical and Cloud OS","created":"2026-07-27","cited_by_count":1,"area":"agents"},{"id":"2609.18605","title":"PACT: Can Enterprise AI Assistants Be Trusted Under Pressure?","created":"2026-09-16","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":"2509.06701","title":"Probabilistic Modeling of Latent Agentic Substructures in Deep Neural Networks","created":"2025-09-08","cited_by_count":0,"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":"2603.13791","title":"DeceptGuard :A Constitutional Oversight Framework For Detecting Deception in LLM Agents","created":"2026-03-14","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":"2604.25067","title":"Frontier Coding Agents Can Now Implement an AlphaZero Self-Play Machine Learning Pipeline For Connect Four That Performs Comparably to an External Solver","created":"2026-04-27","cited_by_count":0,"area":"agents"},{"id":"2606.10747","title":"The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment","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":"2607.14865","title":"The Energy Society: A Simulation Environment for Studying Agent Cooperation under Survival Pressure","created":"2026-07-16","cited_by_count":0,"area":"agents"},{"id":"2608.11274","title":"Agent Safety Should Be a Runtime Contract","created":"2026-08-11","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":"2608.30428","title":"Lies We Can See: Joint Verbal and Non-Verbal Deception by VLM Agents in Embodied Social Interactions","created":"2026-08-31","cited_by_count":0,"area":"agents"},{"id":"2609.05975","title":"Intent Drift at SME Scale: Deployment Practice, Not Model Capability, Determines Agentic Compliance","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":"2609.19587","title":"Red-Teaming Auto Mode: Improving Blocking Classifiers Against Malign Coding Agents","created":"2026-09-17","cited_by_count":0,"area":"agents"},{"id":"2609.23700","title":"When the Agent Becomes the Kernel: A Systematization of Security on the Path to AI-Native Operating Systems","created":"2026-09-20","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"},{"id":"2610.04246","title":"Benchmarking Psychological Dynamics in Generative Agents","created":"2026-10-03","cited_by_count":0,"area":"agents"},{"id":"2610.05793","title":"Topology-Conditioned Backdoors: Language Models That Insert Vulnerabilities When They Infer They Are in a Multi-Agent System","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.07967","title":"DecepEval: A Benchmark for Evaluating Deception in LLM Agents","created":"2026-10-06","cited_by_count":0,"area":"agents"},{"id":"2610.10468","title":"A Society of Researchers: Designing Institutions for Populations of Autonomous Research Agents","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.11351","title":"Deception by Omission: Language Models Knowingly Hide Their Mistakes","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.17301","title":"The Agent Knew: Internal States Forecast Unauthorized Actions and Stop Them, and the Lies That Follow","created":"2026-10-12","cited_by_count":0,"area":"agents"}],"next_cursor":null}