{"total":57,"rows":[{"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":"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":"2505.15216","title":"BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems","created":"2025-05-21","cited_by_count":40,"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":"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":"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":"2505.17107","title":"CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution","created":"2025-05-21","cited_by_count":14,"area":"agents"},{"id":"2603.11214","title":"Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenarios","created":"2026-03-11","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":"2604.20801","title":"Synthesizing Multi-Agent Harnesses for Vulnerability Discovery","created":"2026-04-22","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":"2508.05674","title":"Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF Benchmark","created":"2025-08-05","cited_by_count":12,"area":"agents"},{"id":"2510.24317","title":"Cybersecurity AI Benchmark (CAIBench): A Meta-Benchmark for Evaluating Cybersecurity AI Agents","created":"2025-10-28","cited_by_count":12,"area":"agents"},{"id":"2505.18384","title":"Dynamic Risk Assessments for Offensive Cybersecurity Agents","created":"2025-05-23","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":"2508.02921","title":"PentestJudge: Judging Agent Behavior Against Operational Requirements","created":"2025-08-04","cited_by_count":7,"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":"2512.11143","title":"Automated Penetration Testing with LLM Agents and Classical Planning","created":"2025-12-11","cited_by_count":5,"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":"2510.02389","title":"From Trace to Line: LLM Agent for Real-World OSS Vulnerability Localization","created":"2025-09-30","cited_by_count":4,"area":"agents"},{"id":"2510.14700","title":"LLM Agents for Automated Web Vulnerability Reproduction: Are We There Yet?","created":"2025-10-16","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":"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":"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":"2510.12200","title":"HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities","created":"2025-10-14","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":"2608.02407","title":"Antares: Foundation Models for Agentic Vulnerability Localization","created":"2026-08-03","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":"2603.21551","title":"AI In Cybersecurity Education -- Scalable Agentic CTF Design Principles and Educational Outcomes","created":"2026-03-23","cited_by_count":1,"area":"agents"},{"id":"2606.02644","title":"A New Framework for Cybersecurity Refusals in AI Agents","created":"2026-05-31","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":"2608.04317","title":"Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)","created":"2026-08-05","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":"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":"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":"2605.26195","title":"CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Fly","created":"2026-05-25","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":"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":"2609.15939","title":"Vulnerability Localization Benchmark: Measuring Agentic Security Analysis at Repository Scale","created":"2026-09-14","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":"2609.25591","title":"Evaluating Coding Agents on Kernel Exploit Generation","created":"2026-09-22","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":"2609.36635","title":"WitnessGym: Benchmarking Coding Agents on the Construction of Bug Witnesses","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.14350","title":"Natural Code Transformation Confuses Agents in Vulnerability Analysis","created":"2026-10-09","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}