{"total":92,"rows":[{"id":"2410.09024","title":"AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents","created":"2024-10-11","cited_by_count":437,"area":"agents"},{"id":"2602.12670","title":"SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks","created":"2026-02-13","cited_by_count":315,"area":"agents"},{"id":"2507.02825","title":"Establishing Best Practices for Building Rigorous Agentic Benchmarks","created":"2025-07-03","cited_by_count":102,"area":"agents"},{"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":"2510.11977","title":"Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation","created":"2025-10-13","cited_by_count":92,"area":"agents"},{"id":"2506.11791","title":"SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks","created":"2025-06-13","cited_by_count":75,"area":"agents"},{"id":"2409.16165","title":"EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities","created":"2024-09-24","cited_by_count":52,"area":"agents"},{"id":"2412.01778","title":"HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing","created":"2024-12-02","cited_by_count":37,"area":"agents"},{"id":"2605.11086","title":"ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?","created":"2026-05-11","cited_by_count":29,"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":"2512.03262","title":"Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks","created":"2025-12-02","cited_by_count":22,"area":"agents"},{"id":"2502.10931","title":"D-CIPHER: Dynamic Collaborative Intelligent Multi-Agent System with Planner and Heterogeneous Executors for Offensive Security","created":"2025-02-15","cited_by_count":20,"area":"agents"},{"id":"2604.06550","title":"SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills","created":"2026-04-08","cited_by_count":20,"area":"agents"},{"id":"2508.18370","title":"Training Language Model Agents to Find Vulnerabilities with CTF-Dojo","created":"2025-08-25","cited_by_count":15,"area":"agents"},{"id":"2412.02776","title":"Hacking CTFs with Plain Agents","created":"2024-12-03","cited_by_count":14,"area":"agents"},{"id":"2509.22097","title":"SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios","created":"2025-09-26","cited_by_count":13,"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":"2605.26079","title":"Automated Benchmark Auditing for AI Agents and Large Language Models","created":"2026-05-25","cited_by_count":12,"area":"agents"},{"id":"2607.02357","title":"Cloak and Detonate: Scanner Evasion and Dynamic Detection of Agent Skill Malware","created":"2026-07-02","cited_by_count":10,"area":"agents"},{"id":"2505.18384","title":"Dynamic Risk Assessments for Offensive Cybersecurity Agents","created":"2025-05-23","cited_by_count":8,"area":"agents"},{"id":"2508.00935","title":"Measuring Harmfulness of Computer-Using Agents","created":"2025-07-31","cited_by_count":8,"area":"agents"},{"id":"2511.02780","title":"PoCo: Agentic Proof-of-Concept Exploit Generation for Smart Contracts","created":"2025-11-04","cited_by_count":8,"area":"agents"},{"id":"2602.03100","title":"Risky-Bench: Probing Agentic Safety Risks under Real-World Deployment","created":"2026-02-03","cited_by_count":8,"area":"agents"},{"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":"2602.02164","title":"Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM Agents","created":"2026-02-02","cited_by_count":6,"area":"agents"},{"id":"2605.14892","title":"Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems","created":"2026-05-14","cited_by_count":6,"area":"agents"},{"id":"2606.11150","title":"ABC-Bench: An Agentic Bio-Capabilities Benchmark for Biosecurity","created":"2026-06-09","cited_by_count":6,"area":"agents"},{"id":"2607.20911","title":"Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction","created":"2026-07-23","cited_by_count":6,"area":"agents"},{"id":"2502.10420","title":"Position: Stop Acting Like Language Model Agents Are Normal Agents","created":"2025-02-04","cited_by_count":5,"area":"agents"},{"id":"2510.02389","title":"From Trace to Line: LLM Agent for Real-World OSS Vulnerability Localization","created":"2025-09-30","cited_by_count":4,"area":"agents"},{"id":"2604.11950","title":"AnyPoC: Universal Proof-of-Concept Test Generation for Scalable LLM-Based Bug Detection","created":"2026-04-13","cited_by_count":4,"area":"agents"},{"id":"2604.18718","title":"Towards Optimal Agentic Architectures for Offensive Security Tasks","created":"2026-04-20","cited_by_count":4,"area":"agents"},{"id":"2605.11504","title":"CTFusion: A CTF-based Benchmark for LLM Agent Evaluation","created":"2026-05-12","cited_by_count":4,"area":"agents"},{"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":"2602.05523","title":"Capture the Flags: Family-Based Evaluation of Agentic LLMs via Semantics-Preserving Transformations","created":"2026-02-05","cited_by_count":3,"area":"agents"},{"id":"2602.08023","title":"CTFExplorer: Evaluating LLM Offensive Agents Through Multi-Target Web CTF Benchmarking","created":"2026-02-08","cited_by_count":3,"area":"agents"},{"id":"2604.19354","title":"Do Agents Dream of Root Shells? Partial-Credit Evaluation of LLM Agents in Capture the Flag Challenges","created":"2026-04-21","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":"2605.22643","title":"Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety","created":"2026-05-21","cited_by_count":3,"area":"agents"},{"id":"2607.07774","title":"ScopeJudge: Cost-Aware Pre-Execution Gating for Offensive Security Agents","created":"2026-07-08","cited_by_count":3,"area":"agents"},{"id":"2510.12200","title":"HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities","created":"2025-10-14","cited_by_count":2,"area":"agents"},{"id":"2512.06659","title":"The Evolution of Agentic AI in Cybersecurity: From Single LLM Reasoners to Multi-Agent Systems and Autonomous Pipelines","created":"2025-12-07","cited_by_count":2,"area":"agents"},{"id":"2605.10597","title":"CrackMeBench: Binary Reverse Engineering for Agents","created":"2026-05-11","cited_by_count":2,"area":"agents"},{"id":"2605.21497","title":"Autonomous LLM Agents & CTFs: A Second Look","created":"2026-04-29","cited_by_count":2,"area":"agents"},{"id":"2606.03811","title":"AI Agents Enable Adaptive Computer Worms","created":"2026-06-02","cited_by_count":2,"area":"agents"},{"id":"2510.17521","title":"Cybersecurity AI: Evaluating Agentic Cybersecurity in Attack/Defense CTFs","created":"2025-10-20","cited_by_count":1,"area":"agents"},{"id":"2601.06910","title":"PenForge: On-the-Fly Expert Agent Construction for Automated Penetration Testing","created":"2026-01-11","cited_by_count":1,"area":"agents"},{"id":"2603.13384","title":"VulnAgent-R2: Evidence-Calibrated Multi-Agent Auditing for Repository-Level Vulnerability Detection","created":"2026-03-11","cited_by_count":1,"area":"agents"},{"id":"2603.17673","title":"Towards Reliable Local Security Agents: Verifiable Post-Training for Linux Privilege Escalation","created":"2026-03-18","cited_by_count":1,"area":"agents"},{"id":"2603.22577","title":"STRIATUM-CTF: A Protocol-Driven Agentic Framework for General-Purpose CTF Solving","created":"2026-03-23","cited_by_count":1,"area":"agents"},{"id":"2605.06486","title":"Autonomous Adversary: Red-Teaming in the age of LLM","created":"2026-05-07","cited_by_count":1,"area":"agents"},{"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":"2606.17114","title":"An Evaluation of Data Leakage Risks in Tool-Using LLM Agents in Realistic Scenarios","created":"2026-06-15","cited_by_count":1,"area":"agents"},{"id":"2606.19899","title":"Measuring Biological Capabilities and Risks of AI Agents","created":"2026-06-18","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":"2607.26791","title":"SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response","created":"2026-07-29","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":"2608.11469","title":"The Next Challenge for Agentic Cybersecurity: A Realistic, Contamination-Free Reverse Engineering Benchmark","created":"2026-08-11","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":"2608.26237","title":"How Do LLM Agents Actually Get the Flag? Trace-Level Provenance for Agentic Offensive Security Evaluation","created":"2026-08-26","cited_by_count":1,"area":"agents"},{"id":"2609.05818","title":"Agentic BAIM-LLM Evaluation (ABLE): Benchmarking LLM Use of Protein Design Tools","created":"2026-09-05","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":"2510.01654","title":"SoK: Measuring What Matters for Closed-Loop Security Agents","created":"2025-10-02","cited_by_count":0,"area":"agents"},{"id":"2602.18172","title":"Can AI Lower the Barrier to Cybersecurity? A Human-Centered Mixed-Methods Study of Novice CTF Learning","created":"2026-02-20","cited_by_count":0,"area":"agents"},{"id":"2603.28998","title":"Design Principles for the Construction of a Benchmark Evaluating Security Operation Capabilities of Multi-agent AI Systems","created":"2026-03-30","cited_by_count":0,"area":"agents"},{"id":"2604.17159","title":"Systematic Capability Benchmarking of Frontier Large Language Models for Offensive Cyber Tasks","created":"2026-04-18","cited_by_count":0,"area":"agents"},{"id":"2604.25067","title":"Frontier Coding Agents Can Now Implement an AlphaZero Self-Play Machine Learning Pipeline For Connect Four That Performs Comparably to an External Solver","created":"2026-04-27","cited_by_count":0,"area":"agents"},{"id":"2605.10834","title":"From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World","created":"2026-05-11","cited_by_count":0,"area":"agents"},{"id":"2605.19722","title":"Measuring Safety Alignment Effects in Autonomous Security Agents","created":"2026-05-19","cited_by_count":0,"area":"agents"},{"id":"2605.31593","title":"Stateful Online Monitoring Catches Distributed Agent Attacks","created":"2026-05-29","cited_by_count":0,"area":"agents"},{"id":"2606.16420","title":"Transferable Self-Evolving Playbooks for Agentic Security Auditing","created":"2026-06-15","cited_by_count":0,"area":"agents"},{"id":"2607.02873","title":"Determinants and Limits of LLM Security-Tool Orchestration: A Study with HexStrike-AI","created":"2026-07-03","cited_by_count":0,"area":"agents"},{"id":"2607.26314","title":"StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents","created":"2026-07-28","cited_by_count":0,"area":"agents"},{"id":"2608.09567","title":"From Runnable to Verifiable: An Independent Reproducibility Study of LLM/Agent-Driven Vulnerability Validation Artifacts","created":"2026-08-10","cited_by_count":0,"area":"agents"},{"id":"2608.21423","title":"Agentic Security: A Systematization of Tools, Failure Modes, and Design Laws for LLM-Driven Penetration Testing","created":"2026-08-16","cited_by_count":0,"area":"agents"},{"id":"2608.23181","title":"CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild","created":"2026-08-24","cited_by_count":0,"area":"agents"},{"id":"2609.01185","title":"Reveree: Diagnosing LLM Reverse-Engineering Agents","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.11852","title":"BlueSTAR: Tiered Agentic Architecture for Autonomous Cyber Defense","created":"2026-09-10","cited_by_count":0,"area":"agents"},{"id":"2609.22792","title":"SelfOp: An Optimization Algorithm for Self-Improving Security Agents","created":"2026-09-19","cited_by_count":0,"area":"agents"},{"id":"2609.23953","title":"Agents That Edit Documents: Measuring Agentic PDF Forgery Against a Non-Agentic Control","created":"2026-09-20","cited_by_count":0,"area":"agents"},{"id":"2609.23980","title":"MobileCybench: Evaluating Agent Vulnerability Discovery via Executable Probes","created":"2026-09-21","cited_by_count":0,"area":"agents"},{"id":"2609.28572","title":"Where Cyber Agents Struggle: Bottleneck Analysis of Multi-Stage LLM Agents","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.32424","title":"CyberClear: A Benchmark for LLM Agent Systems on APT Attack Chain Provenance","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.32776","title":"On the Behavioral Traits of LLM Agents","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.33446","title":"HESP: Separating What to Probe from When to Stop in Local LLM Alert-Triage Agents","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.35909","title":"Cheap to Hypothesize, Costly to Verify: The Defense Surface of Agentic Vulnerability Discovery","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.36635","title":"WitnessGym: Benchmarking Coding Agents on the Construction of Bug Witnesses","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.17020","title":"CWE-bench: Refocusing Agentic Security from Exploitation to Defense","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.17837","title":"ProtoArena: Can AI Agents Discover and Exploit Real-World Cross-Component Protocol Vulnerabilities?","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}