{"total":16,"rows":[{"id":"2603.00729","title":"Qwen3-Coder-Next Technical Report","created":"2026-02-28","cited_by_count":71,"area":"agents"},{"id":"2410.13886","title":"Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents","created":"2024-10-11","cited_by_count":65,"area":"agents"},{"id":"2605.14153","title":"ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents","created":"2026-05-13","cited_by_count":19,"area":"agents"},{"id":"2507.14201","title":"ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation","created":"2025-07-14","cited_by_count":15,"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":"2506.00739","title":"DefenderBench: A Toolkit for Evaluating Language Agents in Cybersecurity Environments","created":"2025-05-31","cited_by_count":4,"area":"agents"},{"id":"2603.13517","title":"CTI-REALM: Benchmark to Evaluate Agent Performance on Security Detection Rule Generation Capabilities","created":"2026-03-13","cited_by_count":4,"area":"agents"},{"id":"2601.07880","title":"Sola-Visibility-ISPM: Benchmarking Agentic AI for Identity Security Posture Management Visibility","created":"2026-01-11","cited_by_count":3,"area":"agents"},{"id":"2606.02674","title":"Cross-Vendor Sola ISPM Benchmark: Evaluating Agentic AI for Federated Identity Security Reasoning","created":"2026-06-01","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":"2608.18613","title":"CTIFoundry: An Agent-Native Corpus Scaffold for Cyber Threat Intelligence","created":"2026-08-19","cited_by_count":2,"area":"agents"},{"id":"2601.21083","title":"OpenSec: Measuring Incident Response Agent Calibration Under Adversarial Evidence","created":"2026-01-28","cited_by_count":1,"area":"agents"},{"id":"2603.18235","title":"Toward Reliable, Safe, and Secure LLMs for Scientific Applications","created":"2026-03-18","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":"2603.14417","title":"Questionnaire Responses Do not Capture the Safety of AI Agents","created":"2026-03-15","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"}],"next_cursor":null}