{"total":96,"rows":[{"id":"2507.02825","title":"Establishing Best Practices for Building Rigorous Agentic Benchmarks","created":"2025-07-03","cited_by_count":102,"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":"2507.22358","title":"Magentic-UI: Towards Human-in-the-loop Agentic Systems","created":"2025-07-30","cited_by_count":43,"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":"2508.19461","title":"Reliable Weak-to-Strong Monitoring of LLM Agents","created":"2025-08-26","cited_by_count":31,"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":"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":"2605.14153","title":"ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents","created":"2026-05-13","cited_by_count":19,"area":"agents"},{"id":"2509.01835","title":"From CVE Entries to Verifiable Exploits: An Automated Multi-Agent Framework for Reproducing CVEs","created":"2025-09-01","cited_by_count":18,"area":"agents"},{"id":"2603.02277","title":"Quantifying Frontier LLM Capabilities for Container Sandbox Escape","created":"2026-03-01","cited_by_count":18,"area":null},{"id":"2509.09853","title":"SWE-Effi: Re-Evaluating Software AI Agent System Effectiveness Under Resource Constraints","created":"2025-09-11","cited_by_count":17,"area":"agents"},{"id":"2604.07223","title":"TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories","created":"2026-04-08","cited_by_count":16,"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":"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":"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":"2507.15241","title":"FaultLine: Automated Proof-of-Vulnerability Generation Using LLM Agents","created":"2025-07-21","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":"2602.03012","title":"CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability","created":"2026-02-03","cited_by_count":9,"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":"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":"2510.11688","title":"PACEbench: A Framework for Evaluating Practical AI Cyber-Exploitation Capabilities","created":"2025-10-13","cited_by_count":7,"area":null},{"id":"2603.04915","title":"EVMbench: Evaluating AI Agents on Smart Contract Security","created":"2026-03-05","cited_by_count":7,"area":null},{"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":"2505.11449","title":"LLMs unlock new paths to monetizing exploits","created":"2025-05-16","cited_by_count":5,"area":null},{"id":"2505.19395","title":"VADER: A Human-Evaluated Benchmark for Vulnerability Assessment, Detection, Explanation, and Remediation","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2507.17257","title":"Agent Identity Evals: Measuring Agentic Identity","created":"2025-07-23","cited_by_count":5,"area":"agents"},{"id":"2510.06607","title":"Your Harness is Not Secure: Benchmarking Real-world Threat of Command Line Interface Agent","created":"2025-10-08","cited_by_count":5,"area":"agents"},{"id":"2512.21132","title":"AutoBaxBuilder: Bootstrapping Code Security Benchmarking","created":"2025-12-24","cited_by_count":5,"area":"synth"},{"id":"2609.08149","title":"SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents","created":"2026-09-08","cited_by_count":5,"area":"agents"},{"id":"2512.22211","title":"With Great Capabilities Come Great Responsibilities: Introducing the Agentic Risk & Capability Framework for Governing Agentic AI Systems","created":"2025-12-22","cited_by_count":4,"area":"agents"},{"id":"2602.02262","title":"OmniCode: A Benchmark for Evaluating Software Engineering Agents","created":"2026-02-02","cited_by_count":4,"area":"agents"},{"id":"2603.02297","title":"ZeroDayBench: Evaluating LLM Agents on Unseen Zero-Day Vulnerabilities for Cyberdefense","created":"2026-03-02","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":"2606.14295","title":"AgentCyberRange: Benchmarking Frontier AI Systems in Realistic Cyber Ranges","created":"2026-06-12","cited_by_count":4,"area":null},{"id":"2508.20643","title":"CyberSleuth: Autonomous Blue-Team LLM Agent for Web Attack Forensics","created":"2025-08-28","cited_by_count":3,"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":"2509.16275","title":"SecureFixAgent: A Hybrid LLM Agent for Automated Python Static Vulnerability Repair","created":"2025-09-18","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":"2602.13574","title":"Execution-State-Aware LLM Reasoning for Automated Proof-of-Vulnerability Generation","created":"2026-02-14","cited_by_count":3,"area":"lr"},{"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":"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":"2509.06921","title":"Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunities","created":"2025-09-08","cited_by_count":2,"area":null},{"id":"2603.15921","title":"VIBEPASS: Can Vibe Coders Really Pass the Vibe Check?","created":"2026-03-16","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":"2607.26998","title":"AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Penetration Agents","created":"2026-07-29","cited_by_count":2,"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":"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":"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":"2603.17974","title":"Toward Scalable Automated Repository-Level Datasets for Software Vulnerability Detection","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2603.18235","title":"Toward Reliable, Safe, and Secure LLMs for Scientific Applications","created":"2026-03-18","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":"2606.02644","title":"A New Framework for Cybersecurity Refusals in AI Agents","created":"2026-05-31","cited_by_count":1,"area":"agents"},{"id":"2606.13757","title":"SEVRA-BENCH: Social Engineering of Vulnerabilities in Review Agents","created":"2026-06-11","cited_by_count":1,"area":"agents"},{"id":"2607.04729","title":"RustMizan: A Compilable, Contamination-Aware Benchmarking Framework for Rust Vulnerabilities","created":"2026-07-06","cited_by_count":1,"area":"agents"},{"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":"2607.27518","title":"Automated Transcript Analysis for Detecting Flaws in Agentic Benchmarks","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":"2608.09526","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":"2508.15808","title":"Uplifted Attackers, Human Defenders: The Cyber Offense-Defense Balance for Trailing-Edge Organizations","created":"2025-08-14","cited_by_count":0,"area":null},{"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":"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":"2605.11029","title":"FragBench: Cross-Session Attacks Hidden in Benign-Looking Fragments","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.23243","title":"Are Frontier LLMs Ready for Cybersecurity? Evidence for Vertical Foundation Models from Dual-Mode Vulnerability Benchmarks","created":"2026-05-22","cited_by_count":0,"area":null},{"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":"2606.03453","title":"FORGE: Multi-Agent Graduated Exploitation and Detection Engineering","created":"2026-06-02","cited_by_count":0,"area":"agents"},{"id":"2606.13079","title":"The Emergence of Autonomous Penetration Capabilities in Large Language Model-Powered AI Systems","created":"2026-06-11","cited_by_count":0,"area":null},{"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":"2608.12172","title":"Rethinking Agent Security as a Networking Problem","created":"2026-08-12","cited_by_count":0,"area":"agents"},{"id":"2608.15012","title":"SysEvolve: An AI-native, safe, autonomous adversarial attack-defense co-evolutionary system","created":"2026-08-15","cited_by_count":0,"area":null},{"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":"2608.25817","title":"SkillShield: Prompt-Space Security Skills for LLM Coding Agents","created":"2026-08-26","cited_by_count":0,"area":"agents"},{"id":"2608.26882","title":"PLCBench: Can Autonomous LLM Agents Turn PLC Access into Sustained Physical Impact?","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.05335","title":"The History Is the Detector: Executing CVE Patch History, End-to-End","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.06229","title":"SWE-Test: Benchmarking LLM Vulnerability Discovery via Input Prediction","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.08418","title":"Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.20614","title":"Inference-Engine Fingerprinting Attacks are Practical: Exploring Model-Driven Environmental Discovery, Exploitation, and Escape","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.22792","title":"SelfOp: An Optimization Algorithm for Self-Improving Security Agents","created":"2026-09-19","cited_by_count":0,"area":"agents"},{"id":"2609.23980","title":"MobileCybench: Evaluating Agent Vulnerability Discovery via Executable Probes","created":"2026-09-21","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":"2609.35909","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":"2610.14350","title":"Natural Code Transformation Confuses Agents in Vulnerability Analysis","created":"2026-10-09","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"},{"id":"2610.19433","title":"EvoProbe: Evaluation-Driven Benchmark Evolution for LLM Agents","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}