{"total":103,"rows":[{"id":"2409.02977","title":"Large Language Model-Based Agents for Software Engineering: A Survey","created":"2024-09-04","cited_by_count":178,"area":"agents"},{"id":"2406.11147","title":"Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG","created":"2024-06-17","cited_by_count":68,"area":null},{"id":"2501.18160","title":"RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing","created":"2025-01-30","cited_by_count":49,"area":"agents"},{"id":"2502.07049","title":"LLMs in Software Security: A Survey of Vulnerability Detection Techniques and Insights","created":"2025-02-10","cited_by_count":47,"area":null},{"id":"2411.12924","title":"Human-In-the-Loop Software Development Agents","created":"2024-11-19","cited_by_count":42,"area":"agents"},{"id":"2502.11844","title":"BaxBench: Can LLMs Generate Correct and Secure Backends?","created":"2025-02-17","cited_by_count":41,"area":null},{"id":"2502.13681","title":"Repo2Run: Automated Building Executable Environment for Code Repository at Scale","created":"2025-02-19","cited_by_count":39,"area":null},{"id":"2508.11126","title":"AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities","created":"2025-08-15","cited_by_count":28,"area":"agents"},{"id":"2503.09002","title":"KNighter: Transforming Static Analysis with LLM-Synthesized Checkers","created":"2025-03-12","cited_by_count":24,"area":null},{"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":"2506.08311","title":"Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study","created":"2025-06-10","cited_by_count":16,"area":"agents"},{"id":"2504.07137","title":"Large Language Model (LLM) for Software Security: Code Analysis, Malware Analysis, Reverse Engineering","created":"2025-04-07","cited_by_count":15,"area":null},{"id":"2405.20441","title":"SECURE: Benchmarking Large Language Models for Cybersecurity","created":"2024-05-30","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":"2502.18474","title":"A Contemporary Survey of Large Language Model Assisted Program Analysis","created":"2025-02-05","cited_by_count":11,"area":null},{"id":"2512.07533","title":"VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection","created":"2025-12-08","cited_by_count":11,"area":"lr"},{"id":"2412.15004","title":"From Vulnerabilities to Remediation: A Systematic Literature Review of LLMs in Code Security","created":"2024-12-19","cited_by_count":10,"area":null},{"id":"2503.09433","title":"CASTLE: Benchmarking Dataset for Static Code Analyzers and LLMs towards CWE Detection","created":"2025-03-12","cited_by_count":10,"area":null},{"id":"2503.15554","title":"Rethinking the Evaluation of Secure Code Generation","created":"2025-03-18","cited_by_count":10,"area":null},{"id":"2508.21302","title":"Locus: Agentic Predicate Synthesis for Directed Fuzzing","created":"2025-08-29","cited_by_count":9,"area":"agents"},{"id":"2411.06493","title":"LProtector: An LLM-driven Vulnerability Detection System","created":"2024-11-10","cited_by_count":8,"area":null},{"id":"2504.20964","title":"OSVBench: Benchmarking LLMs on Specification Generation Tasks for Operating System Verification","created":"2025-04-29","cited_by_count":8,"area":null},{"id":"2412.10483","title":"Enhancing Automated Loop Invariant Generation for Complex Programs with Large Language Models","created":"2024-12-13","cited_by_count":7,"area":null},{"id":"2503.17885","title":"Reasoning with LLMs for Zero-Shot Vulnerability Detection","created":"2025-03-22","cited_by_count":7,"area":"lr"},{"id":"2506.00714","title":"RFCAudit: An LLM Agent for Functional Bug Detection in Network Protocols","created":"2025-05-31","cited_by_count":7,"area":"agents"},{"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":"2511.00872","title":"A Comprehensive Empirical Evaluation of Agent Frameworks on Code-centric Software Engineering Tasks","created":"2025-11-02","cited_by_count":7,"area":"agents"},{"id":"2607.01641","title":"When Agents Do Not Stop: Uncovering Infinite Agentic Loops in LLM Agents","created":"2026-07-02","cited_by_count":7,"area":"agents"},{"id":"2408.03489","title":"Harnessing the Power of LLMs in Source Code Vulnerability Detection","created":"2024-08-07","cited_by_count":6,"area":null},{"id":"2412.14841","title":"Helping LLMs Improve Code Generation Using Feedback from Testing and Static Analysis","created":"2024-12-19","cited_by_count":6,"area":null},{"id":"2504.13472","title":"CodeVisionary: An Agent-based Framework for Evaluating Large Language Models in Code Generation","created":"2025-04-18","cited_by_count":6,"area":"agents"},{"id":"2506.23644","title":"QLPro: Automated Code Vulnerability Discovery via LLM and Static Code Analysis Integration","created":"2025-06-30","cited_by_count":6,"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":"2510.14036","title":"One Bug, Hundreds Behind: LLMs for Large-Scale Bug Discovery","created":"2025-10-15","cited_by_count":6,"area":null},{"id":"2510.15963","title":"ESCA: Contextualizing Embodied Agents via Scene-Graph Generation","created":"2025-10-11","cited_by_count":6,"area":"mllm"},{"id":"2605.14859","title":"Do Coding Agents Understand Least-Privilege Authorization?","created":"2026-05-14","cited_by_count":6,"area":"agents"},{"id":"2503.12205","title":"PredicateFix: Repairing Static Analysis Alerts with Bridging Predicates","created":"2025-03-15","cited_by_count":5,"area":"rag"},{"id":"2504.13515","title":"Large Language Models for Validating Network Protocol Parsers","created":"2025-04-18","cited_by_count":5,"area":null},{"id":"2504.13676","title":"Trace Gadgets: Minimizing Code Context for Machine Learning-Based Vulnerability Prediction","created":"2025-04-18","cited_by_count":5,"area":null},{"id":"2507.02976","title":"How Safe Are AI-Generated Patches? A Large-scale Study on Security Risks in LLM and Agentic Automated Program Repair on SWE-bench","created":"2025-06-30","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":"2601.18844","title":"Reducing False Positives in Static Bug Detection with LLMs: An Empirical Study in Industry","created":"2026-01-26","cited_by_count":5,"area":null},{"id":"2601.22952","title":"Sifting the Noise: A Comparative Study of LLM Agents in Vulnerability False Positive Filtering","created":"2026-01-30","cited_by_count":5,"area":"agents"},{"id":"2503.14281","title":"XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants","created":"2025-03-18","cited_by_count":4,"area":null},{"id":"2503.21937","title":"Lobster: A GPU-Accelerated Framework for Neurosymbolic Programming","created":"2025-03-27","cited_by_count":4,"area":"lr"},{"id":"2504.11711","title":"The Hitchhiker's Guide to Program Analysis, Part II: Deep Thoughts by LLMs","created":"2025-04-16","cited_by_count":4,"area":null},{"id":"2510.14700","title":"LLM Agents for Automated Web Vulnerability Reproduction: Are We There Yet?","created":"2025-10-16","cited_by_count":4,"area":"agents"},{"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":"2511.04014","title":"VulInstruct: Teaching LLMs Root-Cause Reasoning for Vulnerability Detection via Security Specifications","created":"2025-11-06","cited_by_count":4,"area":"lr"},{"id":"2602.02262","title":"OmniCode: A Benchmark for Evaluating Software Engineering Agents","created":"2026-02-02","cited_by_count":4,"area":"agents"},{"id":"2602.16891","title":"OpenSage: Self-programming Agent Generation Engine","created":"2026-02-18","cited_by_count":4,"area":"agents"},{"id":"2604.11950","title":"AnyPoC: Universal Proof-of-Concept Test Generation for Scalable LLM-Based Bug Detection","created":"2026-04-13","cited_by_count":4,"area":"agents"},{"id":"2510.22944","title":"Is Your Prompt Poisoning Code? Defect Induction Rates and Security Mitigation Strategies","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2601.10865","title":"Multi-Agent Taint Specification Extraction for Vulnerability Detection","created":"2026-01-15","cited_by_count":3,"area":"agents"},{"id":"2605.21779","title":"FuzzingBrain V2: A Multi-Agent LLM System for Automated Vulnerability Discovery and Reproduction","created":"2026-05-20","cited_by_count":3,"area":"agents"},{"id":"2410.09117","title":"REDO: Execution-Free Runtime Error Detection for COding Agents","created":"2024-10-10","cited_by_count":2,"area":"agents"},{"id":"2505.15242","title":"Adaptive Plan-Execute Framework for Smart Contract Security Auditing","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2509.04191","title":"KubeGuard: LLM-Assisted Kubernetes Hardening via Configuration Files and Runtime Logs Analysis","created":"2025-09-04","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":"2505.13766","title":"A Blueprint for AI-Driven Software Quality: Integrating LLMs with Established Standards","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2603.28345","title":"Reachability Across the NL/PL Boundary: A Taxonomy-Driven Dataflow Model for LLM-Integrated Applications","created":"2026-03-30","cited_by_count":1,"area":null},{"id":"2604.06618","title":"PoC-Adapt: Semantic-Aware Automated Vulnerability Reproduction with LLM Multi-Agents and Reinforcement Learning-Driven Adaptive Policy","created":"2026-04-08","cited_by_count":1,"area":"agents"},{"id":"2604.06633","title":"Argus: Reorchestrating Static Analysis via a Multi-Agent Ensemble for Full-Chain Security Vulnerability Detection","created":"2026-04-08","cited_by_count":1,"area":"lr"},{"id":"2605.01892","title":"CyberAId: AI-Driven Cybersecurity for Financial Service Providers","created":"2026-05-03","cited_by_count":1,"area":null},{"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":"2605.18153","title":"Three Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability Detection","created":"2026-05-18","cited_by_count":1,"area":"lr"},{"id":"2606.22263","title":"Revelio: Cost-Efficient Agentic Memory Safety Vulnerability Detection For Repository-Scale Codebases","created":"2026-06-20","cited_by_count":1,"area":"agents"},{"id":"2607.12058","title":"AutoTrace: From Patches to Triggers via Agentic Interprocedural Exploration","created":"2026-07-13","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":"2412.11194","title":"Direction for Detection: A Survey of Automated Vulnerability Detection and all of its Pain Points","created":"2024-12-15","cited_by_count":0,"area":null},{"id":"2503.13660","title":"INPROVF: Leveraging Large Language Models to Repair High-level Robot Controllers from Assumption Violations","created":"2025-03-17","cited_by_count":0,"area":null},{"id":"2505.19625","title":"Search-Based Software Engineering and AI Foundation Models: Current Landscape and Future Roadmap","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2507.21954","title":"Fine-Tuning Code Language Models to Detect Cross-Language Bugs","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2509.13023","title":"Validating Solidity Code Defects using Symbolic and Concrete Execution powered by Large Language Models","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2510.06645","title":"Distilling Lightweight Language Models for C/C++ Vulnerabilities","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2512.12536","title":"Diverse LLMs vs. Vulnerabilities: Who Detects and Fixes Them Better?","created":"2025-12-14","cited_by_count":0,"area":null},{"id":"2602.07513","title":"SPECA: Specification-to-Checklist Agentic Auditing for Multi-Implementation Systems -- A Case Study on Ethereum Clients","created":"2026-02-07","cited_by_count":0,"area":"agents"},{"id":"2602.10787","title":"VulReaD: Knowledge-Graph-guided Software Vulnerability Reasoning and Detection","created":"2026-02-11","cited_by_count":0,"area":"lr"},{"id":"2603.17174","title":"Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning","created":"2026-03-17","cited_by_count":0,"area":"safety"},{"id":"2604.01637","title":"Seclens: Role-specific Evaluation of LLM's for security vulnerablity detection","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.08291","title":"VCAO: Verifier-Centered Agentic Orchestration for Strategic OS Vulnerability Discovery","created":"2026-04-09","cited_by_count":0,"area":"agents"},{"id":"2604.17948","title":"RAVEN: Retrieval-Augmented Vulnerability Exploration Network for Memory Corruption Analysis in User Code and Binary Programs","created":"2026-04-20","cited_by_count":0,"area":"rag"},{"id":"2604.19049","title":"Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery","created":"2026-04-21","cited_by_count":0,"area":"agents"},{"id":"2605.12694","title":"Agentic Interpretation: Lattice-Structured Evidence for LLM-Based Program Analysis","created":"2026-05-12","cited_by_count":0,"area":"agents"},{"id":"2605.12746","title":"CoT-Guard: Small Models for Strong Monitoring","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2605.21392","title":"VIPER-MCP: Detecting and Exploiting Taint-Style Vulnerabilities in Model Context Protocol Servers","created":"2026-05-20","cited_by_count":0,"area":"agents"},{"id":"2605.23931","title":"BODHI: Precise OS Kernel Specification Inference","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.30604","title":"An Organization-Scoped LLM Agent Runtime Architecture for Regulated Cybersecurity Operations","created":"2026-05-28","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":"2606.18619","title":"Code-Augur: Agentic Vulnerability Detection via Specification Inference","created":"2026-06-17","cited_by_count":0,"area":"agents"},{"id":"2607.11308","title":"FlowArk: Boosting Agentic Data-flow Analysis for Android Apps via Context-Aware Knowledge Reuse","created":"2026-07-13","cited_by_count":0,"area":"agents"},{"id":"2607.24964","title":"ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments","created":"2026-07-27","cited_by_count":0,"area":"agents"},{"id":"2608.12246","title":"VICBench: A Multi-Language Benchmark for Code Vulnerability Detection","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.20637","title":"ARQ: Agentic CodeQL Query Refinement for C/C++ Vulnerability Detection","created":"2026-08-21","cited_by_count":0,"area":"agents"},{"id":"2608.22089","title":"On Predicting Vulnerability Severity Using In-Context Learning: An Industrial Case Study","created":"2026-08-22","cited_by_count":0,"area":null},{"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":"2609.05335","title":"The History Is the Detector: Executing CVE Patch History, End-to-End","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.13728","title":"TyPatch: Transforming Patches into Typestate Rules for Kernel Bug Detection","created":"2026-09-12","cited_by_count":0,"area":null}],"next_cursor":"100"}