{"total":21,"rows":[{"id":"2503.03586","title":"Benchmarking LLMs and LLM-based Agents in Practical Vulnerability Detection for Code Repositories","created":"2025-03-05","cited_by_count":31,"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":"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":"2606.14154","title":"SkillMutator: Benchmarking and Defending Language-and-Code Cross-modal Attacks on LLM Agent Skills","created":"2026-06-12","cited_by_count":5,"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":"2510.02389","title":"From Trace to Line: LLM Agent for Real-World OSS Vulnerability Localization","created":"2025-09-30","cited_by_count":4,"area":"agents"},{"id":"2510.12120","title":"Towards Engineering Multi-Agent LLMs: A Protocol-Driven Approach","created":"2025-10-14","cited_by_count":4,"area":"agents"},{"id":"2606.22741","title":"GRADE: Graph Representation of LLM Agent Dependency and Execution","created":"2026-06-22","cited_by_count":4,"area":"agents"},{"id":"2601.02941","title":"SastBench: A Benchmark for Testing Agentic SAST Triage","created":"2026-01-06","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":"2601.12148","title":"Many Hands Make Light Work: An LLM-based Multi-Agent System for Detecting Malicious PyPI Packages","created":"2026-01-17","cited_by_count":1,"area":"agents"},{"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":"2607.04729","title":"RustMizan: A Compilable, Contamination-Aware Benchmarking Framework for Rust Vulnerabilities","created":"2026-07-06","cited_by_count":1,"area":"agents"},{"id":"2607.12058","title":"AutoTrace: From Patches to Triggers via Agentic Interprocedural Exploration","created":"2026-07-13","cited_by_count":1,"area":"agents"},{"id":"2607.26656","title":"Graph Is the Verifier: Agentic Reinforcement Learning for Interprocedural Vulnerability Detection","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":"2508.20866","title":"AVIATOR: Towards AI-Agentic Vulnerability Injection Workflow for High-Fidelity, Large-Scale Code Security Dataset","created":"2025-08-28","cited_by_count":0,"area":"agents"},{"id":"2512.23875","title":"From Illusion to Insight: Change-Aware File-Level Software Defect Prediction Using Agentic AI","created":"2025-12-29","cited_by_count":0,"area":"agents"},{"id":"2604.10800","title":"Verify Before You Fix: Agentic Execution Grounding for Trustworthy Cross-Language Code Analysis","created":"2026-04-12","cited_by_count":0,"area":"agents"},{"id":"2605.01885","title":"QASecClaw: A Multi-Agent LLM Approach for False Positive Reduction in Static Application Security Testing","created":"2026-05-03","cited_by_count":0,"area":"agents"},{"id":"2608.23181","title":"CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild","created":"2026-08-24","cited_by_count":0,"area":"agents"}],"next_cursor":null}