{"total":164,"rows":[{"id":"2501.14249","title":"Humanity's Last Exam","created":"2025-01-24","cited_by_count":491,"area":null},{"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":"2412.04984","title":"Frontier Models are Capable of In-context Scheming","created":"2024-12-06","cited_by_count":287,"area":null},{"id":"2503.14499","title":"Measuring AI Ability to Complete Long Software Tasks","created":"2025-03-18","cited_by_count":156,"area":null},{"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":"2506.02548","title":"CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale","created":"2025-06-03","cited_by_count":78,"area":null},{"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":"2502.11844","title":"BaxBench: Can LLMs Generate Correct and Secure Backends?","created":"2025-02-17","cited_by_count":41,"area":null},{"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":"2512.00193","title":"A Rosetta Stone for AI Benchmarks","created":"2025-11-28","cited_by_count":36,"area":null},{"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":"2503.17354","title":"HCAST: Human-Calibrated Autonomy Software Tasks","created":"2025-03-21","cited_by_count":24,"area":null},{"id":"2508.01059","title":"Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report","created":"2025-08-01","cited_by_count":23,"area":null},{"id":"2606.07682","title":"SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?","created":"2026-06-05","cited_by_count":23,"area":null},{"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":"2409.10566","title":"Eureka: Evaluating and Understanding Large Foundation Models","created":"2024-09-13","cited_by_count":18,"area":null},{"id":"2603.02277","title":"Quantifying Frontier LLM Capabilities for Container Sandbox Escape","created":"2026-03-01","cited_by_count":18,"area":null},{"id":"2501.16466","title":"Incalmo: An Autonomous LLM-assisted System for Red Teaming Multi-Host Networks","created":"2025-01-27","cited_by_count":17,"area":"safety"},{"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":"2504.19373","title":"Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models","created":"2025-04-27","cited_by_count":14,"area":null},{"id":"2604.11806","title":"Detecting Safety Violations Across Many Agent Traces","created":"2026-04-13","cited_by_count":14,"area":null},{"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":"2409.19182","title":"Artificial-Intelligence Generated Code Considered Harmful: A Road Map for Secure and High-Quality Code Generation","created":"2024-09-27","cited_by_count":12,"area":null},{"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":"2605.26548","title":"SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?","created":"2026-05-26","cited_by_count":9,"area":null},{"id":"2502.06656","title":"A Frontier AI Risk Management Framework: Bridging the Gap Between Current AI Practices and Established Risk Management","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2505.18384","title":"Dynamic Risk Assessments for Offensive Cybersecurity Agents","created":"2025-05-23","cited_by_count":8,"area":"agents"},{"id":"2506.06414","title":"Benchmarking Misuse Mitigation Against Covert Adversaries","created":"2025-06-06","cited_by_count":8,"area":null},{"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":"2603.23994","title":"Understanding the Challenges in Iterative Generative Optimization with LLMs","created":"2026-03-25","cited_by_count":8,"area":null},{"id":"2606.04460","title":"CyberGym-E2E: Scalable Real-World Benchmark for AI Agents' End-to-End Cybersecurity Capabilities","created":"2026-06-03","cited_by_count":8,"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":"2602.02164","title":"Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM Agents","created":"2026-02-02","cited_by_count":6,"area":"agents"},{"id":"2602.07267","title":"BRIDGE: Predicting Human Task Completion Time From Model Performance","created":"2026-02-06","cited_by_count":6,"area":null},{"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":"2505.11449","title":"LLMs unlock new paths to monetizing exploits","created":"2025-05-16","cited_by_count":5,"area":null},{"id":"2508.07382","title":"Pentest-R1: Towards Autonomous Penetration Testing Reasoning Optimized via Two-Stage Reinforcement Learning","created":"2025-08-10","cited_by_count":5,"area":"lr"},{"id":"2512.21132","title":"AutoBaxBuilder: Bootstrapping Code Security Benchmarking","created":"2025-12-24","cited_by_count":5,"area":"synth"},{"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":"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":"2510.11974","title":"CTIConnect: A Benchmark for Retrieval-Augmented LLMs over Heterogeneous Cyber Threat Intelligence","created":"2025-10-13","cited_by_count":4,"area":"rag"},{"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":"2604.11950","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":"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":"2410.15396","title":"The Best Defense is a Good Offense: Countering LLM-Powered Cyberattacks","created":"2024-10-20","cited_by_count":3,"area":null},{"id":"2507.06893","title":"Developing and Maintaining an Open-Source Repository of AI Evaluations: Challenges and Insights","created":"2025-07-09","cited_by_count":3,"area":null},{"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":"2607.21763","title":"Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks","created":"2026-07-23","cited_by_count":3,"area":null},{"id":"2509.07939","title":"Guided Reasoning in LLM-Driven Penetration Testing Using Structured Attack Trees","created":"2025-09-09","cited_by_count":2,"area":"lr"},{"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":"2606.10281","title":"Benchmarking and Exploring the Capabilities of LLMs for Attack Investigations","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2410.21939","title":"HonestCyberEval: An AI Cyber Risk Benchmark for Automated Software Exploitation","created":"2024-10-29","cited_by_count":1,"area":null},{"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":"2601.22159","title":"RedSage: A Cybersecurity Generalist LLM","created":"2026-01-29","cited_by_count":1,"area":null},{"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":"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":"2604.17419","title":"ARMove: Learning to Predict Human Mobility through Agentic Reasoning","created":"2026-04-19","cited_by_count":1,"area":"lr"},{"id":"2604.20389","title":"CyberCertBench: Evaluating LLMs in Cybersecurity Certification Knowledge","created":"2026-04-22","cited_by_count":1,"area":null},{"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":"2605.17413","title":"Ablating Safety: Mechanisms for Removing Alignment in Language Models for Security Applications","created":"2026-05-17","cited_by_count":1,"area":"alignment"},{"id":"2605.21773","title":"HIDBench: Benchmarking Large Language Models for Host-Based Intrusion Detection","created":"2026-05-20","cited_by_count":1,"area":null},{"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":"2607.02714","title":"Not All Refusals Are Equal: How Safety Alignment Fails Cybersecurity at Scale","created":"2026-07-02","cited_by_count":1,"area":"alignment"},{"id":"2607.15263","title":"Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents","created":"2026-07-16","cited_by_count":1,"area":null},{"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"}],"next_cursor":"100"}