{"total":62,"rows":[{"id":"2605.18747","title":"Code as Agent Harness","created":"2026-05-18","cited_by_count":47,"area":"agents"},{"id":"2511.02208","title":"Training Proactive and Personalized LLM Agents","created":"2025-11-04","cited_by_count":46,"area":"agents"},{"id":"2507.22358","title":"Magentic-UI: Towards Human-in-the-loop Agentic Systems","created":"2025-07-30","cited_by_count":43,"area":"agents"},{"id":"2606.04990","title":"From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents","created":"2026-06-03","cited_by_count":37,"area":"agents"},{"id":"2602.13379","title":"Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents","created":"2026-02-13","cited_by_count":30,"area":"agents"},{"id":"2602.17753","title":"The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems","created":"2026-02-19","cited_by_count":30,"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":"2510.23883","title":"Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges","created":"2025-10-27","cited_by_count":28,"area":"agents"},{"id":"2604.04759","title":"Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw","created":"2026-04-06","cited_by_count":20,"area":"agents"},{"id":"2510.24411","title":"OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows","created":"2025-10-28","cited_by_count":19,"area":"agents"},{"id":"2607.10487","title":"Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents","created":"2026-07-11","cited_by_count":18,"area":"agents"},{"id":"2604.23338","title":"A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework","created":"2026-04-25","cited_by_count":11,"area":"agents"},{"id":"2601.06663","title":"SafePro: Evaluating the Safety of Professional-Level AI Agents","created":"2026-01-10","cited_by_count":10,"area":"agents"},{"id":"2602.03255","title":"LPS-Bench: Benchmarking Safety Awareness of Computer-Use Agents in Long-Horizon Planning under Benign and Adversarial Scenarios","created":"2026-02-03","cited_by_count":9,"area":"agents"},{"id":"2509.25624","title":"STAC: When Innocent Tools Form Dangerous Chains for LLM Agents","created":"2025-09-30","cited_by_count":8,"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":"2607.01793","title":"Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification","created":"2026-07-02","cited_by_count":7,"area":"agents"},{"id":"2603.08835","title":"MASEval: Extending Multi-Agent Evaluation from Models to Systems","created":"2026-03-09","cited_by_count":6,"area":"agents"},{"id":"2606.16821","title":"How Much Can We Trust LLM Search Agents? Measuring Endorsement Vulnerability to Web Content Manipulation","created":"2026-06-15","cited_by_count":6,"area":"agents"},{"id":"2603.27148","title":"SafetyDrift: Predicting When AI Agents Cross the Line Before They Actually Do","created":"2026-03-28","cited_by_count":5,"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":"2605.15030","title":"WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections","created":"2026-05-14","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":"2512.02282","title":"DialogGuard: Multi-Agent Psychosocial Safety Evaluation of Sensitive LLM Responses","created":"2025-12-01","cited_by_count":3,"area":"agents"},{"id":"2603.18762","title":"ClawTrap: A MITM-Based Red-Teaming Framework for Real-World OpenClaw Security Evaluation","created":"2026-03-19","cited_by_count":3,"area":"agents"},{"id":"2604.08005","title":"Preference Redirection via Attention Concentration: An Attack on Computer Use Agents","created":"2026-04-09","cited_by_count":3,"area":"agents"},{"id":"2605.03952","title":"MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents","created":"2026-05-05","cited_by_count":3,"area":"agents"},{"id":"2605.17986","title":"LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection","created":"2026-05-18","cited_by_count":3,"area":"agents"},{"id":"2607.27294","title":"AgentS4D: Benchmarking Runtime Risks across the Execution Lifecycle of LLM-Based Workspace Agents","created":"2026-07-29","cited_by_count":3,"area":"agents"},{"id":"2608.12851","title":"Practice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents","created":"2026-08-13","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":"2603.18245","title":"Who Tests the Testers? Systematic Enumeration and Coverage Audit of LLM Agent Tool Call Safety","created":"2026-03-18","cited_by_count":2,"area":"agents"},{"id":"2604.24920","title":"SUDP: Secret-Use Delegation Protocol for Agentic Systems","created":"2026-04-27","cited_by_count":2,"area":"agents"},{"id":"2605.17453","title":"Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback","created":"2026-05-17","cited_by_count":2,"area":"agents"},{"id":"2606.20408","title":"NRT-Bench: Benchmarking Multi-Turn Red-Teaming of LLM Operator Agents in Safety-Critical Control Rooms","created":"2026-06-18","cited_by_count":2,"area":"agents"},{"id":"2607.11751","title":"When Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent Systems","created":"2026-07-13","cited_by_count":2,"area":"agents"},{"id":"2608.08160","title":"Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency in Interactive Narratives","created":"2026-08-08","cited_by_count":2,"area":"agents"},{"id":"2601.13981","title":"VirtualCrime: Evaluating the Criminal Potential and Agentic Behaviors of Large Language Models via Sandbox Simulation","created":"2026-01-20","cited_by_count":1,"area":"agents"},{"id":"2602.04197","title":"From Helpfulness to Toxic Proactivity: Diagnosing Behavioral Misalignment in LLM Agents","created":"2026-02-04","cited_by_count":1,"area":"agents"},{"id":"2603.01564","title":"From Secure Agentic AI to Secure Agentic Web: Challenges, Threats, and Future Directions","created":"2026-03-02","cited_by_count":1,"area":"agents"},{"id":"2604.19752","title":"Soft-Label Governance for Distributional Safety in Multi-Agent Systems","created":"2026-03-19","cited_by_count":1,"area":"agents"},{"id":"2606.02380","title":"SPADE-Bench: Evaluating Spontaneous Strategic Deception in Agents via Plan-Action Divergence","created":"2026-06-01","cited_by_count":1,"area":"agents"},{"id":"2607.13594","title":"SAFETY SENTRY: Context-Aware Human Intervention via EXECUTE-ASK-REFUSE Routing","created":"2026-07-15","cited_by_count":1,"area":"agents"},{"id":"2607.19449","title":"Guardrails as Scapegoats: Auditing Unfaithful Safety Refusals in Tool-Augmented LLM Agents","created":"2026-07-21","cited_by_count":1,"area":"agents"},{"id":"2608.16891","title":"Runtime Governance for Agentic AI: Action-Boundary Control with Trusted Provenance and Fail-Closed Execution","created":"2026-05-17","cited_by_count":1,"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":"2605.29224","title":"Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents","created":"2026-05-28","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":"2607.24893","title":"Early Detection of Distributed Backdoors in Multi-Agent LLM Systems: A Characterization Study","created":"2026-07-27","cited_by_count":0,"area":"agents"},{"id":"2608.24275","title":"RePolicy: Reinforcement Learning for Safety-Policy Invocation in Agent Safeguards","created":"2026-08-25","cited_by_count":0,"area":"agents"},{"id":"2609.06059","title":"DAREBench: Deployment-Aware and Reliable Evaluation of Models as Agents","created":"2026-09-05","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":"2609.23700","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":"2609.30137","title":"Screen Before You Serve: Simulation for Production Customer Experience AI Agents at 140M Scale","created":"2026-09-24","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"},{"id":"2609.33039","title":"Agent Safety From Within: Detecting Harmful Trajectories from LLM Internal States","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.34518","title":"SEAD: A State-Based Perspective on Attack and Defense in Tool-Using Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.03153","title":"EvoRiskBench: An Evolving Benchmark for Runtime Security Risks in Workspace Agents","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.11561","title":"Workerville: Towards an Organizational Behavior Account of Agent Safety","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.15134","title":"Lumen-bench: Cross-Lingual Safety Gaps and the Say-Do Problem in Tool-Calling Large Language Models","created":"2026-10-10","cited_by_count":0,"area":"agents"},{"id":"2610.16039","title":"When Agents Talk, Secrets Travel: Topology-Driven Leakage and Recipient-Conditioned Sanitization in Multi-Agent LLM Systems","created":"2026-10-12","cited_by_count":0,"area":"agents"}],"next_cursor":null}