{"total":52,"rows":[{"id":"2412.14470","title":"Agent-SafetyBench: Evaluating the Safety of LLM Agents","created":"2024-12-19","cited_by_count":306,"area":"agents"},{"id":"2503.18666","title":"AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents","created":"2025-03-24","cited_by_count":223,"area":"agents"},{"id":"2507.06134","title":"OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety","created":"2025-07-08","cited_by_count":75,"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":"2508.00500","title":"ProbGuard: Proactive Runtime Monitoring for LLM Agent Safety via Probabilistic Prediction","created":"2025-08-01","cited_by_count":28,"area":"agents"},{"id":"2510.23883","title":"Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges","created":"2025-10-27","cited_by_count":28,"area":"agents"},{"id":"2602.05073","title":"Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities","created":"2026-02-04","cited_by_count":20,"area":"agents"},{"id":"2607.13104","title":"Self-Improvements in Modern Agentic Systems: A Survey","created":"2026-07-14","cited_by_count":19,"area":"agents"},{"id":"2509.25885","title":"SafeMind: Benchmarking and Mitigating Safety Risks in Embodied LLM Agents","created":"2025-09-30","cited_by_count":17,"area":"agents"},{"id":"2604.01438","title":"ClawSafety: \"Safe\" LLMs, Unsafe Agents","created":"2026-04-01","cited_by_count":17,"area":"agents"},{"id":"2505.23559","title":"SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agents","created":"2025-05-29","cited_by_count":16,"area":"agents"},{"id":"2512.21220","title":"RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic","created":"2025-12-24","cited_by_count":14,"area":"agents"},{"id":"2604.16968","title":"On Safety Risks in Experience-Driven Self-Evolving Agents","created":"2026-04-18","cited_by_count":14,"area":"agents"},{"id":"2504.15699","title":"Advancing Embodied Agent Security: From Safety Benchmarks to Input Moderation","created":"2025-04-22","cited_by_count":13,"area":"agents"},{"id":"2507.08270","title":"Agent Safety Alignment via Reinforcement Learning","created":"2025-07-11","cited_by_count":11,"area":"agents"},{"id":"2606.26524","title":"VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skills","created":"2026-06-25","cited_by_count":9,"area":"agents"},{"id":"2508.00935","title":"Measuring Harmfulness of Computer-Using Agents","created":"2025-07-31","cited_by_count":8,"area":"agents"},{"id":"2602.11749","title":"AIR: Improving Agent Safety through Incident Response","created":"2026-02-12","cited_by_count":8,"area":"agents"},{"id":"2504.14773","title":"PLANET: A Collection of Benchmarks for Evaluating LLMs' Planning Capabilities","created":"2025-04-21","cited_by_count":7,"area":"agents"},{"id":"2505.10872","title":"REI-Bench: Can Embodied Agents Understand Vague Human Instructions in Task Planning?","created":"2025-05-16","cited_by_count":7,"area":"agents"},{"id":"2606.10749","title":"Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation","created":"2026-06-09","cited_by_count":7,"area":"agents"},{"id":"2505.17735","title":"SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator","created":"2025-05-23","cited_by_count":6,"area":"agents"},{"id":"2511.21460","title":"MADRA: Multi-Agent Debate for Risk-Aware Embodied Planning","created":"2025-11-26","cited_by_count":6,"area":"agents"},{"id":"2603.28807","title":"SafeClaw-R: Towards Safe and Secure Multi-Agent Personal Assistants","created":"2026-03-28","cited_by_count":6,"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":"2603.25747","title":"BeSafe-Bench: Unveiling Behavioral Safety Risks of Situated Agents in Functional Environments","created":"2026-01-30","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":"2605.30924","title":"EMBGuard: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied Agents","created":"2026-05-29","cited_by_count":3,"area":"agents"},{"id":"2606.22673","title":"AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agent","created":"2026-06-21","cited_by_count":3,"area":"agents"},{"id":"2510.12985","title":"SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of Foundation Model-based Embodied Agents","created":"2025-10-14","cited_by_count":2,"area":"agents"},{"id":"2604.11174","title":"EmbodiedGovBench: A Benchmark for Governance, Recovery, and Upgrade Safety in Embodied Agent Systems","created":"2026-04-13","cited_by_count":2,"area":"agents"},{"id":"2606.04051","title":"RUBAS: Rubric-Based Reinforcement Learning for Agent Safety","created":"2026-06-02","cited_by_count":2,"area":"agents"},{"id":"2609.00028","title":"UI-Venus-2 Technical Report","created":"2026-08-27","cited_by_count":2,"area":"agents"},{"id":"2510.21524","title":"EU-Agent-Bench: Measuring Illegal Behavior of LLM Agents Under EU Law","created":"2025-10-24","cited_by_count":1,"area":"agents"},{"id":"2512.19016","title":"DREAM: Dynamic Red-teaming across Environments for AI Models","created":"2025-12-22","cited_by_count":1,"area":"agents"},{"id":"2606.04037","title":"Toward Pre-Deployment Assurance for Enterprise AI Agents: Ontology-Grounded Simulation and Trust Certification","created":"2026-06-02","cited_by_count":1,"area":"agents"},{"id":"2606.31073","title":"MultiUAV-Plat: An LLM-Oriented Platform, Benchmark and Framework for Multi-UAV Collaborative Task Planning","created":"2026-06-30","cited_by_count":1,"area":"agents"},{"id":"2608.02683","title":"$S^3$: Improving Agent Safety through Multi-Stage Defense","created":"2026-08-03","cited_by_count":1,"area":"agents"},{"id":"2511.18114","title":"ASTRA: Agentic Steerability and Risk Assessment Framework","created":"2025-11-22","cited_by_count":0,"area":"agents"},{"id":"2603.09157","title":"Real-Time Trust Verification for Safe Agentic Actions using TrustBench","created":"2026-03-10","cited_by_count":0,"area":"agents"},{"id":"2605.06992","title":"Why Does Agentic Safety Fail to Generalize Across Tasks?","created":"2026-05-07","cited_by_count":0,"area":"agents"},{"id":"2606.13994","title":"Hidden in Plain Sight: Benchmarking Agent Safety Against Decomposition Attacks with DECOMPBENCH","created":"2026-06-12","cited_by_count":0,"area":"agents"},{"id":"2606.23927","title":"RIFT-Bench: Dynamic Red-teaming For Agentic AI Systems","created":"2026-06-22","cited_by_count":0,"area":"agents"},{"id":"2609.22724","title":"MATE: Policy-Aware Security Auditing for Mobile Agents via Synthesis-Driven Trajectory Learning","created":"2026-09-19","cited_by_count":0,"area":"agents"},{"id":"2609.23894","title":"Connecting the Dots in Agentic AI Security: A Cross-Dimensional Threat Taxonomy, Evaluation Maturity, and Open Challenges","created":"2026-09-20","cited_by_count":0,"area":"agents"},{"id":"2609.27847","title":"Security and Privacy in Large-Model-Driven Embodied Agents: Attacks, Defenses, and Future Directions","created":"2026-08-19","cited_by_count":0,"area":"agents"},{"id":"2609.35889","title":"SINGED: Correct Outputs Do Not Certify Safe Execution in LLM Agents","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2610.02664","title":"A GHOST in Long-Horizon Agents: Governance Hazard from Overlooked Safety Constraints across Turns","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.06122","title":"Benchmarking Jailbreak Guardrails for Embodied Agents","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.08928","title":"Multi-Aspect Runtime Verification for Simulation-Based V&V of LLM-Enabled Autonomous Agents","created":"2026-10-06","cited_by_count":0,"area":"agents"},{"id":"2610.09294","title":"RT-Safe: Benchmarking Agent Safety in Real-Time Embodied Environment","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.15150","title":"Harmony Harness: Multi-Objective Self-Evolution of Agent Harnesses","created":"2026-10-10","cited_by_count":0,"area":"agents"}],"next_cursor":null}