{"total":55,"rows":[{"id":"2504.19678","title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","created":"2025-04-28","cited_by_count":149,"area":"lr"},{"id":"2504.21039","title":"Llama-3.1-FoundationAI-SecurityLLM-Base-8B Technical Report","created":"2025-04-28","cited_by_count":31,"area":null},{"id":"2508.01059","title":"Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report","created":"2025-08-01","cited_by_count":23,"area":null},{"id":"2412.20787","title":"SecBench: A Comprehensive Multi-Dimensional Benchmarking Dataset for LLMs in Cybersecurity","created":"2024-12-30","cited_by_count":21,"area":null},{"id":"2507.19060","title":"PurpCode: Reasoning for Safer Code Generation","created":"2025-07-25","cited_by_count":18,"area":"lr"},{"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":"2502.15797","title":"OCCULT: Evaluating Large Language Models for Offensive Cyber Operation Capabilities","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2509.20166","title":"CyberSOCEval: Benchmarking LLMs Capabilities for Malware Analysis and Threat Intelligence Reasoning","created":"2025-09-24","cited_by_count":12,"area":"lr"},{"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":"2506.08354","title":"Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning","created":"2025-06-10","cited_by_count":10,"area":null},{"id":"2601.22975","title":"Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text","created":"2026-01-30","cited_by_count":10,"area":"lr"},{"id":"2509.10858","title":"Large Language Models for Security Operations Centers: A Comprehensive Survey","created":"2025-09-13","cited_by_count":9,"area":null},{"id":"2505.18384","title":"Dynamic Risk Assessments for Offensive Cybersecurity Agents","created":"2025-05-23","cited_by_count":8,"area":"agents"},{"id":"2505.20630","title":"SV-TrustEval-C: Evaluating Structure and Semantic Reasoning in Large Language Models for Source Code Vulnerability Analysis","created":"2025-05-27","cited_by_count":8,"area":"lr"},{"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":"2509.23571","title":"Benchmarking LLM-Assisted Blue Teaming via Standardized Threat Hunting","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2410.15490","title":"Dynamic Intelligence Assessment: Benchmarking LLMs on the Road to AGI with a Focus on Model Confidence","created":"2024-10-20","cited_by_count":5,"area":null},{"id":"2503.23175","title":"Large Language Models Are Unreliable for Cyber Threat Intelligence","created":"2025-03-29","cited_by_count":5,"area":null},{"id":"2412.00652","title":"Multi-Agent Collaboration in Incident Response with Large Language Models","created":"2024-12-01","cited_by_count":4,"area":"agents"},{"id":"2503.03170","title":"AttackSeqBench: Benchmarking the Capabilities of LLMs for Attack Sequences Understanding","created":"2025-03-05","cited_by_count":4,"area":null},{"id":"2505.19973","title":"DFIR-Metric: A Benchmark Dataset for Evaluating Large Language Models in Digital Forensics and Incident Response","created":"2025-05-26","cited_by_count":4,"area":null},{"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":"2507.02964","title":"Less Data, More Security: Advancing Cybersecurity LLMs Specialization via Resource-Efficient Domain-Adaptive Continuous Pre-training with Minimal Tokens","created":"2025-06-30","cited_by_count":4,"area":null},{"id":"2510.11974","title":"CTIConnect: A Benchmark for Retrieval-Augmented LLMs over Heterogeneous Cyber Threat Intelligence","created":"2025-10-13","cited_by_count":4,"area":"rag"},{"id":"2510.14113","title":"Toward Cybersecurity-Expert Small Language Models","created":"2025-10-15","cited_by_count":4,"area":null},{"id":"2511.01144","title":"AthenaBench: A Dynamic Benchmark for Evaluating LLMs in Cyber Threat Intelligence","created":"2025-11-03","cited_by_count":4,"area":null},{"id":"2503.09334","title":"CyberLLMInstruct: A Pseudo-malicious Dataset Revealing Safety-performance Trade-offs in Cyber Security LLM Fine-tuning","created":"2025-03-12","cited_by_count":3,"area":null},{"id":"2506.10467","title":"Specification and Evaluation of Multi-Agent LLM Systems -- Prototype and Cybersecurity Applications","created":"2025-06-12","cited_by_count":3,"area":"lr"},{"id":"2508.13118","title":"AutoBnB-RAG: Enhancing Multi-Agent Incident Response with Retrieval-Augmented Generation","created":"2025-08-18","cited_by_count":3,"area":"rag"},{"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":"2504.14039","title":"MEQA: A Meta-Evaluation Framework for Question & Answer LLM Benchmarks","created":"2025-04-18","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":"2510.27080","title":"Adapting Large Language Models to Emerging Cybersecurity using Retrieval Augmented Generation","created":"2025-10-31","cited_by_count":2,"area":"rag"},{"id":"2602.00513","title":"Minerva: Reinforcement Learning with Verifiable Rewards for Cyber Threat Intelligence LLMs","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2505.11565","title":"ACSE-Eval: Can LLMs threat model real-world cloud infrastructure?","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2509.25241","title":"Fine-tuning of Large Language Models for Domain-Specific Cybersecurity Knowledge","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2510.23443","title":"A Neuro-Symbolic Multi-Agent Approach to Legal-Cybersecurity Knowledge Integration","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2510.26941","title":"LLM-based Multi-class Attack Analysis and Mitigation Framework in IoT/IIoT Networks","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2512.10998","title":"SCOUT: A Defense Against Data Poisoning Attacks in Fine-Tuned Language Models","created":"2025-12-10","cited_by_count":1,"area":"safety"},{"id":"2601.22159","title":"RedSage: A Cybersecurity Generalist LLM","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2604.01977","title":"RuleForge: Automated Generation and Validation for Web Vulnerability Detection at Scale","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2604.20389","title":"CyberCertBench: Evaluating LLMs in Cybersecurity Certification Knowledge","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2506.08320","title":"How Good LLM-Generated Password Policies Are?","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2509.05331","title":"ForensicsData: A Digital Forensics Dataset for Large Language Models","created":"2025-08-31","cited_by_count":0,"area":null},{"id":"2511.06212","title":"RAG-targeted Adversarial Attack on LLM-based Threat Detection and Mitigation Framework","created":"2025-11-09","cited_by_count":0,"area":"safety"},{"id":"2512.21238","title":"Assessing the Software Security Comprehension of Large Language Models","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2601.09029","title":"Proactively Detecting Threats: A Novel Approach Using LLMs","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2603.00051","title":"LitBench: A Graph-Centric Large Language Model Benchmarking Tool For Literature Tasks","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2604.08454","title":"Less Data Approximates More: Earning Faithful Confidence in High-Stakes Domains","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.14166","title":"Hierarchical Retrieval Augmented Generation for Adversarial Technique Annotation in Cyber Threat Intelligence Text","created":"2026-03-24","cited_by_count":0,"area":"rag"},{"id":"2605.00072","title":"XekRung Technical Report","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.24765","title":"CyberMaskQA: A Privacy-Aware Benchmark for Evaluating Large Language Models in Cybersecurity Question Answering","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2607.03233","title":"Agentic and Generative AI for Open-Source Intelligence and Cyber Investigations: Taxonomy, Evaluation, Challenges, and Future Directions","created":"2026-07-03","cited_by_count":0,"area":"agents"},{"id":"2607.20448","title":"Domyn-Small: A European 10B Reasoning Language Model","created":"2026-05-13","cited_by_count":0,"area":"lr"},{"id":"2609.33521","title":"LLM4Trust: Exploring the Capabilities of Large Language Models for Trust Evaluation","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}