{"total":18,"rows":[{"id":"2506.15740","title":"SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents","created":"2025-06-17","cited_by_count":71,"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":"2506.05296","title":"Control Tax: The Price of Keeping AI in Check","created":"2025-06-05","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":"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":"2607.02514","title":"Distributed Attacks in Persistent-State AI Control","created":"2026-07-02","cited_by_count":5,"area":"agents"},{"id":"2605.09684","title":"MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring","created":"2026-05-10","cited_by_count":4,"area":"agents"},{"id":"2609.00038","title":"trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories","created":"2026-08-29","cited_by_count":2,"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":"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":"2610.01023","title":"Groundability, Not Scale Alone: When Weak Reviewers Can Audit Strong Coding Agents","created":"2026-10-01","cited_by_count":1,"area":"agents"},{"id":"2608.10530","title":"On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models","created":"2026-08-11","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":"2609.18272","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":"2610.07089","title":"Towards a Unified Misuse Monitoring Benchmark","created":"2026-10-05","cited_by_count":0,"area":"agents"}],"next_cursor":null}