{"total":23,"rows":[{"id":"2604.07223","title":"TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories","created":"2026-04-08","cited_by_count":16,"area":"agents"},{"id":"2410.09114","title":"Catastrophic Cyber Capabilities Benchmark (3CB): Robustly Evaluating LLM Agent Cyber Offense Capabilities","created":"2024-10-10","cited_by_count":12,"area":"agents"},{"id":"2510.26396","title":"A Pragmatic View of AI Personhood","created":"2025-10-30","cited_by_count":12,"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":"2510.17017","title":"SafeSearch: Do Not Trade Safety for Utility in LLM Search Agents","created":"2025-10-19","cited_by_count":9,"area":"agents"},{"id":"2602.22303","title":"Training Agents to Self-Report Misbehavior","created":"2026-02-25","cited_by_count":6,"area":"agents"},{"id":"2606.01317","title":"SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces","created":"2026-05-31","cited_by_count":6,"area":"agents"},{"id":"2608.24777","title":"StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing","created":"2026-08-25","cited_by_count":6,"area":"agents"},{"id":"2605.09278","title":"EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium","created":"2026-05-10","cited_by_count":4,"area":"agents"},{"id":"2605.16282","title":"Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents","created":"2026-04-11","cited_by_count":4,"area":"agents"},{"id":"2606.23189","title":"Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity?","created":"2026-06-22","cited_by_count":3,"area":"agents"},{"id":"2510.03485","title":"Learning Efficient Guardrails for Compliance","created":"2025-10-03","cited_by_count":2,"area":"agents"},{"id":"2510.11851","title":"Deep Research Agents Brings Deeper Harm","created":"2025-10-13","cited_by_count":2,"area":"agents"},{"id":"2606.02644","title":"A New Framework for Cybersecurity Refusals in AI Agents","created":"2026-05-31","cited_by_count":1,"area":"agents"},{"id":"2609.33658","title":"AgentBoundary: Counterfactual Evaluation of Safety in Tool-Using LLM Agents","created":"2026-09-27","cited_by_count":1,"area":"agents"},{"id":"2604.19049","title":"Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery","created":"2026-04-21","cited_by_count":0,"area":"agents"},{"id":"2606.25836","title":"AI Snitches Get Glitches: Towards Evading Agentic Surveillance","created":"2026-06-24","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":"2607.29199","title":"Alignment Is Local: A Paired Diagnostic for GUI Agents under User-Side Persuasion","created":"2026-07-31","cited_by_count":0,"area":"agents"},{"id":"2608.16068","title":"CAPO: Constraint-Aware Prompt Optimization for LLM Agents","created":"2026-08-17","cited_by_count":0,"area":"agents"},{"id":"2609.14157","title":"When Tools Get in the Way: The Effect of Unnecessary Tool Availability on LLM Answering","created":"2026-09-12","cited_by_count":0,"area":"agents"},{"id":"2609.14758","title":"Fabrication After Tool Failure: Tool-Augmented Agents Assert Values Their Tools Did Not Return","created":"2026-09-13","cited_by_count":0,"area":"agents"},{"id":"2609.33017","title":"Trust and Task Completion in the World of Consumer AI Agents","created":"2026-09-26","cited_by_count":0,"area":"agents"}],"next_cursor":null}