{"total":19,"rows":[{"id":"2604.12374","title":"Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2026-04-14","cited_by_count":38,"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":"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":"2507.07441","title":"SAND: Boosting LLM Agents with Self-Taught Action Deliberation","created":"2025-07-10","cited_by_count":14,"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":"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":"2602.22303","title":"Training Agents to Self-Report Misbehavior","created":"2026-02-25","cited_by_count":6,"area":"agents"},{"id":"2507.20796","title":"Aligning Large Language Model Agents with Rational and Moral Preferences: A Supervised Fine-Tuning Approach","created":"2025-07-28","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":"2602.16943","title":"Mind the GAP: Text Safety Does Not Transfer to Tool-Call Safety in LLM Agents","created":"2026-02-18","cited_by_count":3,"area":"agents"},{"id":"2510.09474","title":"Multimodal Policy Internalization for Conversational Agents","created":"2025-10-10","cited_by_count":2,"area":"agents"},{"id":"2510.11588","title":"Analyzing and Internalizing Complex Policy Documents for LLM Agents","created":"2025-10-13","cited_by_count":2,"area":"agents"},{"id":"2606.20470","title":"Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems","created":"2026-06-18","cited_by_count":2,"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":"2603.14417","title":"Questionnaire Responses Do not Capture the Safety of AI Agents","created":"2026-03-15","cited_by_count":0,"area":"agents"},{"id":"2606.28739","title":"Agent Safety Is Action Alignment","created":"2026-06-27","cited_by_count":0,"area":"agents"},{"id":"2609.27994","title":"Compliant with Local Controls, Collectively Discriminatory. A Governance Architecture for Multi-Agent AI in Regulated Finance","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.32520","title":"When Users Change Their Minds: Measuring and Repairing Intent Drift in LLM Agents","created":"2026-09-26","cited_by_count":0,"area":"agents"}],"next_cursor":null}