{"total":26,"rows":[{"id":"2510.05179","title":"Agentic Misalignment: How LLMs Could Be Insider Threats","created":"2025-10-05","cited_by_count":158,"area":"agents"},{"id":"2504.13203","title":"X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents","created":"2025-04-15","cited_by_count":125,"area":"agents"},{"id":"2603.11088","title":"The Attack and Defense Landscape of Agentic AI: A Comprehensive Survey","created":"2026-03-11","cited_by_count":28,"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":"2603.19469","title":"A Framework for Formalizing LLM Agent Security","created":"2026-03-19","cited_by_count":16,"area":"agents"},{"id":"2602.14161","title":"When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift","created":"2026-02-15","cited_by_count":11,"area":"agents"},{"id":"2504.20965","title":"AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security","created":"2025-04-29","cited_by_count":10,"area":"agents"},{"id":"2510.08240","title":"The Alignment Waltz: Jointly Training Agents to Collaborate for Safety","created":"2025-10-09","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":"2602.22303","title":"Training Agents to Self-Report Misbehavior","created":"2026-02-25","cited_by_count":6,"area":"agents"},{"id":"2506.20606","title":"Model Editing as a Double-Edged Sword: Steering Agent Ethical Behavior Toward Beneficence or Harm","created":"2025-06-25","cited_by_count":2,"area":"agents"},{"id":"2603.15968","title":"MAC: Multi-Agent Constitution Learning","created":"2026-03-16","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":"2602.15689","title":"A Content-Based Framework for Cybersecurity Refusal Decisions in Large Language Models","created":"2026-02-17","cited_by_count":1,"area":"agents"},{"id":"2607.05518","title":"aiAuthZ: Off-Host, Identity-Bound Authorization for AI Agents","created":"2026-07-06","cited_by_count":1,"area":"agents"},{"id":"2507.15885","title":"ADEPTS: A Capability Framework for Human-Centered Agent Design","created":"2025-07-18","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":"2604.18847","title":"Human-Guided Harm Recovery for Computer Use Agents","created":"2026-04-20","cited_by_count":0,"area":"agents"},{"id":"2605.01644","title":"Toward a Principled Framework for Agent Safety Measurement","created":"2026-05-02","cited_by_count":0,"area":"agents"},{"id":"2605.31593","title":"Stateful Online Monitoring Catches Distributed Agent Attacks","created":"2026-05-29","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":"2607.05462","title":"BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment","created":"2026-07-06","cited_by_count":0,"area":"agents"},{"id":"2609.18820","title":"Compositional Policy Violations: When Step-Level Compliance Fails In Agentic AI Workflows","created":"2026-09-16","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":"2610.07089","title":"Towards a Unified Misuse Monitoring Benchmark","created":"2026-10-05","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"}],"next_cursor":null}