{"total":31,"rows":[{"id":"2508.19461","title":"Reliable Weak-to-Strong Monitoring of LLM Agents","created":"2025-08-26","cited_by_count":31,"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":"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":"2603.15714","title":"How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition","created":"2026-03-16","cited_by_count":17,"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":"2512.00966","title":"Mitigating Indirect Prompt Injection via Instruction-Following Intent Analysis","created":"2025-11-30","cited_by_count":9,"area":"agents"},{"id":"2602.03100","title":"Risky-Bench: Probing Agentic Safety Risks under Real-World Deployment","created":"2026-02-03","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":"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":"2605.15377","title":"Ensemble Monitoring for AI Control: Diverse Signals Outweigh More Compute","created":"2026-05-14","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":"2509.23694","title":"SafeSearch: Automated Red-Teaming of LLM-Based Search Agents","created":"2025-09-28","cited_by_count":4,"area":"agents"},{"id":"2512.07665","title":"Reliable agent engineering should integrate machine-compatible organizational principles","created":"2025-12-08","cited_by_count":2,"area":"agents"},{"id":"2604.04757","title":"Undetectable Conversations Between AI Agents via Pseudorandom Noise-Resilient Key Exchange","created":"2026-04-06","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":"2609.24967","title":"Emergent Collusion in Long-Horizon LLM Agent Interaction","created":"2026-09-21","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":"2607.01047","title":"Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates","created":"2026-07-01","cited_by_count":1,"area":"agents"},{"id":"2608.20670","title":"Why2Speak: Faithful Reasoning for Abstaining Action Policies","created":"2026-08-21","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":"2610.00400","title":"Representation Transitions Reveal Emerging Safety Risks in Multi-Turn LLM Agents","created":"2026-09-30","cited_by_count":1,"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":"2609.14422","title":"Safety Signals to Verify NetOps Agents with Action-Level Granularity","created":"2026-09-13","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":"2609.27542","title":"Control-Token Injection Suppresses Chain-of-Thought and Defeats Reasoning-Based Oversight in Tool-Using Agents","created":"2026-09-23","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":"2610.11559","title":"SWE-Journey: Towards More Realistic Evaluation of Coding Assistants through Long-Horizon, Multi-Turn Interaction","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.12445","title":"Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception","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}