{"total":128,"rows":[{"id":"2507.21504","title":"Evaluation and Benchmarking of LLM Agents: A Survey","created":"2025-07-29","cited_by_count":152,"area":"agents"},{"id":"2407.19354","title":"The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies","created":"2024-07-28","cited_by_count":131,"area":"agents"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2503.17332","title":"CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities","created":"2025-03-21","cited_by_count":96,"area":"agents"},{"id":"2406.01637","title":"Teams of LLM Agents can Exploit Zero-Day Vulnerabilities","created":"2024-06-02","cited_by_count":95,"area":"agents"},{"id":"2408.02479","title":"From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future","created":"2024-08-05","cited_by_count":86,"area":"agents"},{"id":"2405.03644","title":"When LLMs Meet Cybersecurity: A Systematic Literature Review","created":"2024-05-06","cited_by_count":71,"area":null},{"id":"2408.01605","title":"CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models","created":"2024-08-02","cited_by_count":58,"area":null},{"id":"2502.07049","title":"LLMs in Software Security: A Survey of Vulnerability Detection Techniques and Insights","created":"2025-02-10","cited_by_count":47,"area":null},{"id":"2501.10114","title":"Infrastructure for AI Agents","created":"2025-01-17","cited_by_count":41,"area":null},{"id":"2501.13411","title":"VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Framework","created":"2025-01-23","cited_by_count":31,"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":"2510.23883","title":"Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges","created":"2025-10-27","cited_by_count":28,"area":"agents"},{"id":"2502.20383","title":"Why Are Web AI Agents More Vulnerable Than Standalone LLMs? A Security Analysis","created":"2025-02-27","cited_by_count":27,"area":"agents"},{"id":"2409.14457","title":"Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends","created":"2024-09-22","cited_by_count":26,"area":null},{"id":"2410.14569","title":"When LLMs Go Online: The Emerging Threat of Web-Enabled LLMs","created":"2024-10-18","cited_by_count":24,"area":"agents"},{"id":"2504.05408","title":"Frontier AI's Impact on the Cybersecurity Landscape","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2510.06445","title":"A Survey on Agentic Security: Applications, Threats and Defenses","created":"2025-10-07","cited_by_count":20,"area":"agents"},{"id":"2508.03153","title":"Estimating Worst-Case Frontier Risks of Open-Weight LLMs","created":"2025-08-05","cited_by_count":19,"area":null},{"id":"2407.05694","title":"On the Limitations of Compute Thresholds as a Governance Strategy","created":"2024-07-08","cited_by_count":18,"area":null},{"id":"2408.08902","title":"Audit-LLM: Multi-Agent Collaboration for Log-based Insider Threat Detection","created":"2024-08-12","cited_by_count":18,"area":"agents"},{"id":"2406.12263","title":"Defending Against Social Engineering Attacks in the Age of LLMs","created":"2024-06-18","cited_by_count":15,"area":null},{"id":"2512.09882","title":"Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing","created":"2025-12-10","cited_by_count":15,"area":null},{"id":"2405.20441","title":"SECURE: Benchmarking Large Language Models for Cybersecurity","created":"2024-05-30","cited_by_count":14,"area":null},{"id":"2410.21060","title":"CTINexus: Automatic Cyber Threat Intelligence Knowledge Graph Construction Using Large Language Models","created":"2024-10-28","cited_by_count":14,"area":null},{"id":"2504.10112","title":"Benchmarking Practices in LLM-driven Offensive Security: Testbeds, Metrics, and Experiment Design","created":"2025-04-14","cited_by_count":14,"area":null},{"id":"2503.15552","title":"Personalized Attacks of Social Engineering in Multi-turn Conversations: LLM Agents for Simulation and Detection","created":"2025-03-18","cited_by_count":13,"area":"agents"},{"id":"2502.15797","title":"OCCULT: Evaluating Large Language Models for Offensive Cyber Operation Capabilities","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2507.15241","title":"FaultLine: Automated Proof-of-Vulnerability Generation Using LLM Agents","created":"2025-07-21","cited_by_count":12,"area":"agents"},{"id":"2410.17141","title":"Towards Automated Penetration Testing: Introducing LLM Benchmark, Analysis, and Improvements","created":"2024-10-22","cited_by_count":11,"area":null},{"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":"2405.10295","title":"Societal Adaptation to Advanced AI","created":"2024-05-16","cited_by_count":10,"area":null},{"id":"2510.02609","title":"RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents","created":"2025-10-02","cited_by_count":9,"area":"agents"},{"id":"2505.18384","title":"Dynamic Risk Assessments for Offensive Cybersecurity Agents","created":"2025-05-23","cited_by_count":8,"area":"agents"},{"id":"2408.04125","title":"VulScribeR: Exploring RAG-based Vulnerability Augmentation with LLMs","created":"2024-08-07","cited_by_count":7,"area":null},{"id":"2408.05061","title":"A Jailbroken GenAI Model Can Cause Substantial Harm: GenAI-powered Applications are Vulnerable to PromptWares","created":"2024-08-09","cited_by_count":7,"area":"safety"},{"id":"2505.06913","title":"RedTeamLLM: an Agentic AI framework for offensive security","created":"2025-05-11","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":"2408.11650","title":"CIPHER: Cybersecurity Intelligent Penetration-testing Helper for Ethical Researcher","created":"2024-08-21","cited_by_count":6,"area":null},{"id":"2410.10871","title":"Applying Refusal-Vector Ablation to Llama 3.1 70B Agents","created":"2024-10-08","cited_by_count":6,"area":"agents"},{"id":"2509.23573","title":"Uncovering Vulnerabilities of LLM-Assisted Cyber Threat Intelligence","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2603.07557","title":"AgentRaft: Automated Detection of Data Over-Exposure in LLM Agents","created":"2026-03-08","cited_by_count":6,"area":"agents"},{"id":"2605.09104","title":"Token Economics for LLM Agents: A Dual-View Study from Computing and Economics","created":"2026-05-09","cited_by_count":6,"area":"agents"},{"id":"2606.01494","title":"ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree","created":"2026-05-31","cited_by_count":6,"area":null},{"id":"2409.00985","title":"Co-Learning: Code Learning for Multi-Agent Reinforcement Collaborative Framework with Conversational Natural Language Interfaces","created":"2024-09-02","cited_by_count":5,"area":"agents"},{"id":"2501.07058","title":"Logic Meets Magic: LLMs Cracking Smart Contract Vulnerabilities","created":"2025-01-13","cited_by_count":5,"area":null},{"id":"2602.09433","title":"Autonomous Action Runtime Management(AARM):A System Specification for Securing AI-Driven Actions at Runtime","created":"2026-02-10","cited_by_count":5,"area":null},{"id":"2411.12820","title":"Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation","created":"2024-11-19","cited_by_count":4,"area":null},{"id":"2412.08653","title":"What AI evaluations for preventing catastrophic risks can and cannot do","created":"2024-11-26","cited_by_count":4,"area":null},{"id":"2503.04299","title":"Mapping AI Benchmark Data to Quantitative Risk Estimates Through Expert Elicitation","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2506.00739","title":"DefenderBench: A Toolkit for Evaluating Language Agents in Cybersecurity Environments","created":"2025-05-31","cited_by_count":4,"area":"agents"},{"id":"2506.02048","title":"Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges","created":"2025-06-01","cited_by_count":4,"area":"agents"},{"id":"2510.14700","title":"LLM Agents for Automated Web Vulnerability Reproduction: Are We There Yet?","created":"2025-10-16","cited_by_count":4,"area":"agents"},{"id":"2511.01144","title":"AthenaBench: A Dynamic Benchmark for Evaluating LLMs in Cyber Threat Intelligence","created":"2025-11-03","cited_by_count":4,"area":null},{"id":"2511.15998","title":"Hiding in the AI Traffic: Abusing MCP for LLM-Powered Agentic Red Teaming","created":"2025-11-20","cited_by_count":4,"area":"agents"},{"id":"2604.05719","title":"Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing","created":"2026-04-07","cited_by_count":4,"area":null},{"id":"2604.18718","title":"Towards Optimal Agentic Architectures for Offensive Security Tasks","created":"2026-04-20","cited_by_count":4,"area":"agents"},{"id":"2606.14295","title":"AgentCyberRange: Benchmarking Frontier AI Systems in Realistic Cyber Ranges","created":"2026-06-12","cited_by_count":4,"area":null},{"id":"2609.28940","title":"Calibrated Decision Models for Autonomous Penetration-Testing Harnesses: JEV and Laya as System One Decision Layers for LLM-Driven Pentest Agents","created":"2026-09-24","cited_by_count":4,"area":"agents"},{"id":"2504.12143","title":"ARCeR: an Agentic RAG for the Automated Definition of Cyber Ranges","created":"2025-04-16","cited_by_count":3,"area":"agents"},{"id":"2507.02977","title":"LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance","created":"2025-06-30","cited_by_count":3,"area":null},{"id":"2509.13021","title":"xOffense: An Autonomous Multi-Agent Framework for Penetration Testing with Domain-Adapted Large Language Models","created":"2025-09-16","cited_by_count":3,"area":"agents"},{"id":"2510.17862","title":"When \"Correct\" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?","created":"2025-10-15","cited_by_count":3,"area":"agents"},{"id":"2511.08475","title":"Designing LLM-based Multi-Agent Systems for Software Engineering Tasks: Quality Attributes, Design Patterns and Rationale","created":"2025-11-11","cited_by_count":3,"area":"agents"},{"id":"2604.03121","title":"An Independent Safety Evaluation of Kimi K2.5","created":"2026-04-03","cited_by_count":3,"area":"agents"},{"id":"2409.02375","title":"How Privacy-Savvy Are Large Language Models? A Case Study on Compliance and Privacy Technical Review","created":"2024-09-04","cited_by_count":2,"area":null},{"id":"2410.23472","title":"Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2506.10330","title":"Augmenting Large Language Models with Static Code Analysis for Automated Code Quality Improvements","created":"2025-06-12","cited_by_count":2,"area":null},{"id":"2605.24949","title":"APT-Agent: Automated Penetration Testing using Large Language Models","created":"2026-05-24","cited_by_count":2,"area":"agents"},{"id":"2408.08619","title":"PatUntrack: Automated Generating Patch Examples for Issue Reports without Tracked Insecure Code","created":"2024-08-16","cited_by_count":1,"area":null},{"id":"2410.07612","title":"A Survey for Deep Reinforcement Learning Based Network Intrusion Detection","created":"2024-09-25","cited_by_count":1,"area":"deeprl"},{"id":"2410.18312","title":"Countering Autonomous Cyber Threats","created":"2024-10-23","cited_by_count":1,"area":null},{"id":"2502.08886","title":"Generative AI for Internet of Things Security: Challenges and Opportunities","created":"2025-02-13","cited_by_count":1,"area":null},{"id":"2502.15506","title":"Construction and Evaluation of LLM-based agents for Semi-Autonomous penetration testing","created":"2025-02-21","cited_by_count":1,"area":"agents"},{"id":"2510.13257","title":"GRIDAI: Generating and Repairing Intrusion Detection Rules via Collaboration among Multiple LLM-based Agents","created":"2025-10-15","cited_by_count":1,"area":"agents"},{"id":"2601.04254","title":"Scaling Trends for Multi-Hop Contextual Reasoning in Mid-Scale Language Models","created":"2026-01-06","cited_by_count":1,"area":"lr"},{"id":"2601.22720","title":"AEGIS: White-Box Attack Path Generation using LLMs and Training Effectiveness Evaluation for Large-Scale Cyber Defence Exercises","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2602.02595","title":"To Defend Against Cyber Attacks, We Must Teach AI Agents to Hack","created":"2026-02-01","cited_by_count":1,"area":"safety"},{"id":"2602.05721","title":"A Dual-Loop Agent Framework for Automated Vulnerability Reproduction","created":"2026-02-05","cited_by_count":1,"area":"agents"},{"id":"2602.13033","title":"Buy versus Build an LLM: A Decision Framework for Governments","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2604.06019","title":"CritBench: A Framework for Evaluating Cybersecurity Capabilities of Large Language Models in IEC 61850 Digital Substation Environments","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2605.01892","title":"CyberAId: AI-Driven Cybersecurity for Financial Service Providers","created":"2026-05-03","cited_by_count":1,"area":null},{"id":"2605.07830","title":"CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios","created":"2026-05-08","cited_by_count":1,"area":"agents"},{"id":"2605.30096","title":"How Reliable Are AI Attackers Against a Fixed Vulnerable Target? A 400-Run Empirical Study of LLM Penetration Testing Consistency","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.25332","title":"Decoupling Reconnaissance and Exploitation: Measuring the Capability Boundaries of LLM-Based Web Penetration Testing","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2607.12406","title":"Isolation as a First-Class Principle for LLM-Agent System Safety: Concepts, Taxonomy, Challenges and Future Directions","created":"2026-07-14","cited_by_count":1,"area":"agents"},{"id":"2607.18575","title":"RECEIPT: Deterministic, Reward-Hacking-Resistant Verification for White-Box Agentic XSS Discovery","created":"2026-07-20","cited_by_count":1,"area":"agents"},{"id":"2607.25379","title":"Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response","created":"2026-07-28","cited_by_count":1,"area":"agents"},{"id":"2608.03009","title":"Tiny Enough to Break In: Agentic Remote Access Trojans Powered by Small Language Models","created":"2026-08-04","cited_by_count":1,"area":"agents"},{"id":"2608.04317","title":"Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)","created":"2026-08-05","cited_by_count":1,"area":"agents"},{"id":"2608.09526","title":"RangeFactory: Scalable Construction of Multi-Hop Cyber Ranges","created":"2026-08-10","cited_by_count":1,"area":"agents"},{"id":"2608.20563","title":"Beyond End-to-End Success: Diagnosing Failures in Long-Horizon Security LLM Agents","created":"2026-08-20","cited_by_count":1,"area":"agents"},{"id":"2609.22664","title":"From Capability to Assurance in Autonomous Penetration-Testing Harnesses: A Framework and Reference Implementation","created":"2026-09-19","cited_by_count":1,"area":"agents"},{"id":"2506.08693","title":"Recognition Without Mitigation: Ethical Frameworks in Autonomous Offensive-LLM Agent Research","created":"2025-06-10","cited_by_count":0,"area":"agents"},{"id":"2509.07933","title":"Breaking Android with AI: A Deep Dive into LLM-Powered Exploitation","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2510.01654","title":"SoK: Measuring What Matters for Closed-Loop Security Agents","created":"2025-10-02","cited_by_count":0,"area":"agents"},{"id":"2601.12607","title":"A Cloud-based Multi-Agentic Workflow for Science","created":"2026-01-18","cited_by_count":0,"area":"agents"},{"id":"2604.05130","title":"A Multi-Agent Framework for Automated Exploit Generation with Constraint-Guided Comprehension and Reflection","created":"2026-04-06","cited_by_count":0,"area":"agents"},{"id":"2604.28129","title":"Latent Adversarial Detection: Adaptive Probing of LLM Activations for Multi-Turn Attack Detection","created":"2026-04-30","cited_by_count":0,"area":"safety"},{"id":"2605.02346","title":"APIOT: Autonomous Vulnerability Management Across Bare-Metal Industrial OT Networks","created":"2026-05-04","cited_by_count":0,"area":null}],"next_cursor":"100"}