{"total":52,"rows":[{"id":"2501.04227","title":"Agent Laboratory: Using LLM Agents as Research Assistants","created":"2025-01-08","cited_by_count":425,"area":"agents"},{"id":"2410.03859","title":"SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?","created":"2024-10-04","cited_by_count":203,"area":null},{"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":"2510.15994","title":"MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents","created":"2025-10-14","cited_by_count":42,"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":"2512.04123","title":"Measuring Agents in Production","created":"2025-12-02","cited_by_count":37,"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":"2508.03153","title":"Estimating Worst-Case Frontier Risks of Open-Weight LLMs","created":"2025-08-05","cited_by_count":19,"area":null},{"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":"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":"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":"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":"2507.15241","title":"FaultLine: Automated Proof-of-Vulnerability Generation Using LLM Agents","created":"2025-07-21","cited_by_count":12,"area":"agents"},{"id":"2505.10321","title":"AutoPentest: Enhancing Vulnerability Management With Autonomous LLM Agents","created":"2025-05-15","cited_by_count":9,"area":"agents"},{"id":"2502.19414","title":"Can Language Models Falsify? Evaluating Algorithmic Reasoning with Counterexample Creation","created":"2025-02-26","cited_by_count":7,"area":"lr"},{"id":"2506.14682","title":"AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models","created":"2025-06-17","cited_by_count":7,"area":"safety"},{"id":"2508.02921","title":"PentestJudge: Judging Agent Behavior Against Operational Requirements","created":"2025-08-04","cited_by_count":7,"area":"agents"},{"id":"2510.11688","title":"PACEbench: A Framework for Evaluating Practical AI Cyber-Exploitation Capabilities","created":"2025-10-13","cited_by_count":7,"area":null},{"id":"2512.21132","title":"AutoBaxBuilder: Bootstrapping Code Security Benchmarking","created":"2025-12-24","cited_by_count":5,"area":"synth"},{"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":"2602.14012","title":"From SFT to RL: Demystifying the Post-Training Pipeline for LLM-based Vulnerability Detection","created":"2026-02-15","cited_by_count":4,"area":"alignment"},{"id":"2602.16891","title":"OpenSage: Self-programming Agent Generation Engine","created":"2026-02-18","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":"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":"2501.13333","title":"AgentRec: Agent Recommendation Using Sentence Embeddings Aligned to Human Feedback","created":"2025-01-23","cited_by_count":3,"area":"agents"},{"id":"2507.19399","title":"Running in CIRCLE? A Simple Benchmark for LLM Code Interpreter Security","created":"2025-07-25","cited_by_count":2,"area":null},{"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":"2510.17491","title":"Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents","created":"2025-10-20","cited_by_count":2,"area":"lr"},{"id":"2601.09129","title":"KryptoPilot: An Open-World Knowledge-Augmented LLM Agent for Automated Cryptographic Exploitation","created":"2026-01-14","cited_by_count":1,"area":"agents"},{"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":"2602.15689","title":"A Content-Based Framework for Cybersecurity Refusal Decisions in Large Language Models","created":"2026-02-17","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":"2604.14317","title":"Challenges and Future Directions in Agentic Reverse Engineering Systems","created":"2026-04-15","cited_by_count":1,"area":"agents"},{"id":"2604.24212","title":"Empowering Autonomous Debugging Agents with Efficient Dynamic Analysis","created":"2026-04-27","cited_by_count":1,"area":"agents"},{"id":"2605.15097","title":"Veritas: Grounding LLM Agents for Reliable Vulnerability Reasoning over Stripped Binaries","created":"2026-05-14","cited_by_count":1,"area":"lr"},{"id":"2605.15569","title":"Detecting Privilege Escalation in Polyglot Microservices via Agentic Program Analysis","created":"2026-05-15","cited_by_count":1,"area":"agents"},{"id":"2605.29963","title":"Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots","created":"2026-05-28","cited_by_count":1,"area":null},{"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":"2608.04317","title":"Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)","created":"2026-08-05","cited_by_count":1,"area":"agents"},{"id":"2608.20563","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":"2605.05000","title":"Agentic Vulnerability Reasoning on COTS Binaries","created":"2026-05-06","cited_by_count":0,"area":"agents"},{"id":"2605.06601","title":"Patch2Vuln: Agentic Reconstruction of Vulnerabilities from Linux Distribution Binary Patches","created":"2026-05-07","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":"2607.09653","title":"VEXAIoT: Autonomous IoT Vulnerability EXploitation using AI Agents","created":"2026-07-10","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":"2609.32700","title":"CAIRN: Dynamic Fact-Intent DAGs for Multi-Agent Exploration","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"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"}],"next_cursor":null}