{"total":67,"rows":[{"id":"2510.05179","title":"Agentic Misalignment: How LLMs Could Be Insider Threats","created":"2025-10-05","cited_by_count":158,"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":"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":"2504.04072","title":"Among Us: A Sandbox for Measuring and Detecting Agentic Deception","created":"2025-04-05","cited_by_count":26,"area":"agents"},{"id":"2512.13526","title":"Async Control: Stress-testing Asynchronous Control Measures for LLM Agents","created":"2025-12-15","cited_by_count":22,"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":"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":"2506.05296","title":"Control Tax: The Price of Keeping AI in Check","created":"2025-06-05","cited_by_count":10,"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":"2602.06948","title":"Agentic Uncertainty Reveals Agentic Overconfidence","created":"2026-02-06","cited_by_count":9,"area":"agents"},{"id":"2604.15384","title":"LinuxArena: A Control Setting for AI Agents in Live Production Software Environments","created":"2026-04-16","cited_by_count":8,"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":"2506.02546","title":"To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems","created":"2025-06-03","cited_by_count":6,"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":"2512.00520","title":"Toward a Safe Internet of Agents","created":"2025-11-29","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":"2605.15377","title":"Ensemble Monitoring for AI Control: Diverse Signals Outweigh More Compute","created":"2026-05-14","cited_by_count":6,"area":"agents"},{"id":"2605.16626","title":"SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors","created":"2026-05-15","cited_by_count":6,"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":"2607.02514","title":"Distributed Attacks in Persistent-State AI Control","created":"2026-07-02","cited_by_count":5,"area":"agents"},{"id":"2512.22211","title":"With Great Capabilities Come Great Responsibilities: Introducing the Agentic Risk & Capability Framework for Governing Agentic AI Systems","created":"2025-12-22","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":"2510.26752","title":"The Oversight Game: Learning to Cooperatively Balance an AI Agent's Safety and Autonomy","created":"2025-10-30","cited_by_count":3,"area":"agents"},{"id":"2603.02960","title":"Architecting Trust in Artificial Epistemic Agents","created":"2026-03-03","cited_by_count":3,"area":"agents"},{"id":"2603.04582","title":"Self-Attribution Bias: When AI Monitors Go Easy on Themselves","created":"2026-03-04","cited_by_count":3,"area":"agents"},{"id":"2605.22643","title":"Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety","created":"2026-05-21","cited_by_count":3,"area":"agents"},{"id":"2607.07774","title":"ScopeJudge: Cost-Aware Pre-Execution Gating for Offensive Security Agents","created":"2026-07-08","cited_by_count":3,"area":"agents"},{"id":"2607.14166","title":"Stop Means Stop: Measuring and Repairing the Enforcement Gap in Agent-Framework Control Primitives","created":"2026-07-15","cited_by_count":3,"area":"agents"},{"id":"2401.03529","title":"Quantifying stability of non-power-seeking in artificial agents","created":"2024-01-07","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":"2605.12366","title":"Classifier Context Rot: Monitor Performance Degrades with Context Length","created":"2026-05-12","cited_by_count":2,"area":"agents"},{"id":"2605.31170","title":"Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion","created":"2026-05-29","cited_by_count":2,"area":"agents"},{"id":"2608.02698","title":"Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach","created":"2026-08-03","cited_by_count":2,"area":"agents"},{"id":"2506.13774","title":"Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values","created":"2025-06-08","cited_by_count":1,"area":"agents"},{"id":"2605.09045","title":"Containment Verification: AI Safety Guarantees Independent of Alignment","created":"2026-05-09","cited_by_count":1,"area":"agents"},{"id":"2606.06529","title":"Attack Selection in Agentic AI Control Evaluations Meaningfully Decreases Safety","created":"2026-06-03","cited_by_count":1,"area":"agents"},{"id":"2606.31023","title":"Certified Speculative Execution for Untrusted AI Agents","created":"2026-06-30","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":"2607.09766","title":"Norm Enforcement for AI Agents: Robustly Shaping Behavior in Multi-Agent Systems","created":"2026-07-07","cited_by_count":1,"area":"agents"},{"id":"2609.36490","title":"LLMs Learn to Evade Latent Monitors from Prior Feedback Alone","created":"2026-09-29","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":"2603.13791","title":"DeceptGuard :A Constitutional Oversight Framework For Detecting Deception in LLM Agents","created":"2026-03-14","cited_by_count":0,"area":"agents"},{"id":"2605.28807","title":"Calibrating Conservatism for Scalable Oversight","created":"2026-05-27","cited_by_count":0,"area":"agents"},{"id":"2606.15591","title":"Agentic Retrieval and Reinforcement Learned Equation Chains: A Controlled Generation Framework for Complex and Novel Physics Word Problems","created":"2026-06-14","cited_by_count":0,"area":"agents"},{"id":"2607.02389","title":"Steerability via constraints: a substrate for scalable oversight of coding agents","created":"2026-07-02","cited_by_count":0,"area":"agents"},{"id":"2607.26314","title":"StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents","created":"2026-07-28","cited_by_count":0,"area":"agents"},{"id":"2607.28317","title":"One Human, $N$ Agents: Audit-Budget Allocation for LLM Agent Fleets under Miscalibrated, Correlated Confidence","created":"2026-07-30","cited_by_count":0,"area":"agents"},{"id":"2608.27141","title":"Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agents","created":"2026-08-27","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":"2609.14422","title":"Safety Signals to Verify NetOps Agents with Action-Level Granularity","created":"2026-09-13","cited_by_count":0,"area":"agents"},{"id":"2609.15818","title":"Atria Dawn: The Dawn of Agentic Superintelligence","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2609.18272","title":"Who Audits Whom, on What Substrate, with What Evidence? An Independence-Graded Audit Protocol for Agentic AI","created":"2026-09-16","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":"2609.28900","title":"Codetta: High-Capacity, Keyless, and Undetectable Multi-Agent Collusion","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.32379","title":"Measurement Boundaries in LLM Financial Agent Evaluation: Fixed-Tape Execution and Multi-Defect Auditing","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.33371","title":"API Secrets Should Never Become Tokens in the LLM's Vocabulary: A Threat Analysis of API Credential Handling in LLM Agent Systems and an Empirical Evaluation of a Vault-Mediated Execution Boundary","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2610.03894","title":"Proxy Confidence: Auditing Black-Box LLM Agents with a Surrogate's Log-Probabilities","created":"2026-10-02","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":"2610.04575","title":"From Probe Scores to Alarm Policies: Operational Validity of Activation Monitors for Language-Model 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":"2610.16838","title":"Same Operation, Different Permission: Evaluating Whether Guardrails Honor Authorization","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.17727","title":"SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.19591","title":"L3M: A Verifiable Harness and Runtime for Self-Extending and Self-Improving Agents","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}