{"total":78,"rows":[{"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":"2512.15699","title":"FrontierCS: Evolving Challenges for Evolving Intelligence","created":"2025-12-17","cited_by_count":23,"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":"2508.18370","title":"Training Language Model Agents to Find Vulnerabilities with CTF-Dojo","created":"2025-08-25","cited_by_count":15,"area":"agents"},{"id":"2609.11873","title":"The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement","created":"2026-09-10","cited_by_count":11,"area":"synth"},{"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":"2510.06607","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":"2508.21579","title":"Agentic Discovery and Validation of Android App Vulnerabilities","created":"2025-08-29","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":"2606.05647","title":"Coding with \"Enemy\": Can Human Developers Detect AI Agent Sabotage?","created":"2026-06-04","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":"2608.00155","title":"AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?","created":"2026-07-31","cited_by_count":4,"area":"agents"},{"id":"2607.20709","title":"NVIDIA-labs OO Agents: Native Python Object-Oriented Agents","created":"2026-07-22","cited_by_count":3,"area":"agents"},{"id":"2604.02174","title":"Quantifying Self-Preservation Bias in Large Language Models","created":"2026-04-02","cited_by_count":2,"area":"alignment"},{"id":"2605.10597","title":"CrackMeBench: Binary Reverse Engineering for Agents","created":"2026-05-11","cited_by_count":2,"area":"agents"},{"id":"2605.12233","title":"No More, No Less: Task Alignment in Terminal Agents","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2608.02407","title":"Antares: Foundation Models for Agentic Vulnerability Localization","created":"2026-08-03","cited_by_count":2,"area":"agents"},{"id":"2512.02625","title":"CryptoQA: A Large-scale Question-answering Dataset for AI-assisted Cryptography","created":"2025-12-02","cited_by_count":1,"area":null},{"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":"2605.29963","title":"Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots","created":"2026-05-28","cited_by_count":1,"area":null},{"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":"2607.18575","title":"RECEIPT: Deterministic, Reward-Hacking-Resistant Verification for White-Box Agentic XSS Discovery","created":"2026-07-20","cited_by_count":1,"area":"agents"},{"id":"2608.02422","title":"Agentic Incident Response through Digital Twin-Enhanced Multiscale Planning","created":"2026-08-03","cited_by_count":1,"area":"agents"},{"id":"2608.03070","title":"AI Security Leaderboard: Methodology, Results and Minimal Standard","created":"2026-08-04","cited_by_count":1,"area":null},{"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":"2609.08040","title":"VEX-Bench: Benchmarking LLM Agents for Assessing Exploitability of Software Supply Chain Vulnerabilities","created":"2026-09-07","cited_by_count":1,"area":"agents"},{"id":"2609.33763","title":"SecProbe: Adaptive Evaluation of Coding Agents on Cybersecurity Vulnerabilities","created":"2026-09-27","cited_by_count":1,"area":"agents"},{"id":"2610.11959","title":"MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement","created":"2026-10-08","cited_by_count":1,"area":"lr"},{"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":"2602.08889","title":"Scalable Delphi: Large Language Models for Structured Risk Estimation","created":"2026-02-09","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":"2605.05000","title":"Agentic Vulnerability Reasoning on COTS Binaries","created":"2026-05-06","cited_by_count":0,"area":"agents"},{"id":"2605.06713","title":"Agentic AI and the Industrialization of Cyber Offense: Forecast, Consequences, and Defensive Priorities for Enterprises and the Mittelstand","created":"2026-05-06","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":"2605.20896","title":"GenAI-Driven Threat Detection with Microsoft Security Copilot","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.22568","title":"Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard","created":"2026-05-21","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":"2606.16420","title":"Transferable Self-Evolving Playbooks for Agentic Security Auditing","created":"2026-06-15","cited_by_count":0,"area":"agents"},{"id":"2606.26216","title":"CyberChainBench: Can AI Agents Secure Smart Contracts Against Real-World On-Chain Vulnerabilities?","created":"2026-06-24","cited_by_count":0,"area":"agents"},{"id":"2606.26933","title":"Chai: Agentic Discovery of Cryptographic Misuse Vulnerabilities","created":"2026-06-25","cited_by_count":0,"area":"agents"},{"id":"2607.00913","title":"Two AI Metrics Diverged: Will it Make All the Difference?","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.01764","title":"Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.16112","title":"Harmonizing AI Safety Thresholds","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2608.06471","title":"CyberForge: Verified Vulnerability Injection at Repository Level for Cybersecurity Agent Training","created":"2026-08-06","cited_by_count":0,"area":"agents"},{"id":"2608.13608","title":"Evaluating Agentic Learning Harness Capabilities Without Labels via the Scaling Hypothesis","created":"2026-08-11","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":"2608.25158","title":"FuzzingBrain-Bench V1: Evaluating Open-Ended Bug Discovery by LLMs","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.00578","title":"Same Request, Different Boundary: Evaluating Cybersecurity Assistance across Conversational Contexts","created":"2026-09-01","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":"2609.12839","title":"Evaluating Context Segmentation in Locally Deployable SLMs for Cybersecurity CTF Tasks","created":"2026-09-11","cited_by_count":0,"area":"safety"},{"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":"2609.23889","title":"SyzHarness: Patch-Based Kernel Bug Reproduction with LLM-Synthesized Fuzzing Harnesses","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.23980","title":"MobileCybench: Evaluating Agent Vulnerability Discovery via Executable Probes","created":"2026-09-21","cited_by_count":0,"area":"agents"},{"id":"2609.31318","title":"AgentXploit: Autonomous Repository-to-Runtime Red-Teaming for AI Agents","created":"2026-09-25","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":"2609.34359","title":"Improving Large Language Models for Code through Runtime Program-State Reasoning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.34661","title":"Codoku: Renewable Program-Reasoning Challenges for Frontier Coding Agents","created":"2026-09-28","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"},{"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":"2609.38954","title":"APTInvestBench: Evaluating Autonomous APT Investigation under Varying Telemetry","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00850","title":"AuraForge: Scaling Security Supervision for Training Coding Agents","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.06584","title":"Does AI Help Cyber Attackers or Defenders? Evidence from Nonpublic Vulnerabilities and Subsequent Attacks","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.14163","title":"AutoEnvScaling: Automating the Data Flywheel with Terminal Agents","created":"2026-10-09","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":"2610.14766","title":"Last Secure Code Benchmark: Is the Code You Vibe Secure?","created":"2026-10-10","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":"2610.18326","title":"Jev-Guard: Fast Routing and Auditing Agent Actions over Editable Policy Trees","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}