{"total":14,"rows":[{"id":"2401.10019","title":"R-Judge: Benchmarking Safety Risk Awareness for LLM Agents","created":"2024-01-18","cited_by_count":288,"area":"agents"},{"id":"2510.09781","title":"Building a Foundational Guardrail for General Agentic Systems via Synthetic Data","created":"2025-10-10","cited_by_count":29,"area":"agents"},{"id":"2606.28733","title":"Agentic Abstention: Do Agents Know When to Stop Instead of Act?","created":"2026-06-27","cited_by_count":15,"area":"agents"},{"id":"2409.03793","title":"Safeguarding AI Agents: Developing and Analyzing Safety Architectures","created":"2024-09-03","cited_by_count":3,"area":"agents"},{"id":"2512.20293","title":"AprielGuard","created":"2025-12-23","cited_by_count":2,"area":"agents"},{"id":"2508.15526","title":"SafetyFlow: An Agent-Flow System for Automated LLM Safety Benchmarking","created":"2025-08-21","cited_by_count":1,"area":"agents"},{"id":"2604.16870","title":"Governed MCP: Kernel-Level Tool Governance for AI Agents via Logit-Based Safety Primitives","created":"2026-04-18","cited_by_count":1,"area":"agents"},{"id":"2603.05240","title":"GCAgent: Enhancing Group Chat Communication through Dialogue Agents System","created":"2026-03-05","cited_by_count":0,"area":"agents"},{"id":"2604.22154","title":"Reliable Self-Harm Risk Screening via Adaptive Multi-Agent LLM Systems","created":"2026-04-24","cited_by_count":0,"area":"agents"},{"id":"2605.30848","title":"LLM Anonymization Against Agentic Re-Identification","created":"2026-05-29","cited_by_count":0,"area":"agents"},{"id":"2607.22545","title":"Semalith v1.4: A Calibrated 184M Safety Classifier Achieving State-of-the-Art Prompt-Injection Detection at 44x Fewer Parameters than Llama-Guard-3-8B","created":"2026-05-06","cited_by_count":0,"area":"agents"},{"id":"2609.27773","title":"Beyond Unsafe Detection: Counterfactually Anchored Evidence Attribution for Multi-Turn LLM Safety Failures","created":"2026-08-17","cited_by_count":0,"area":"agents"},{"id":"2609.34241","title":"AdaGuard: An Adaptive Guard Model with User-defined Policies","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.05586","title":"AgentDoxx: Agentic Re-identification of Anonymized Text with Web Search","created":"2026-10-04","cited_by_count":0,"area":"agents"}],"next_cursor":null}