{"total":16,"rows":[{"id":"2506.11791","title":"SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks","created":"2025-06-13","cited_by_count":75,"area":"agents"},{"id":"2602.03012","title":"CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability","created":"2026-02-03","cited_by_count":9,"area":"agents"},{"id":"2504.07634","title":"Agent That Debugs: Dynamic State-Guided Vulnerability Repair","created":"2025-04-10","cited_by_count":7,"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":"2601.02941","title":"SastBench: A Benchmark for Testing Agentic SAST Triage","created":"2026-01-06","cited_by_count":3,"area":"agents"},{"id":"2510.25423","title":"What Challenges Do Developers Face in AI Agent Systems? An Empirical Study on Stack Overflow & GitHub Issues","created":"2025-10-29","cited_by_count":2,"area":"agents"},{"id":"2605.30105","title":"EvoRepair: Enhancing Vulnerability Repair Agents Through Experience-Based Self-Evolution","created":"2026-05-28","cited_by_count":2,"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":"2606.22647","title":"RAVEN: Agentic RAG for Automated Vulnerability Repair","created":"2026-06-21","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":"2607.29422","title":"AgenticRepair: Multi-Faceted Program Context Engineering for Agentic Vulnerability Repair","created":"2026-07-31","cited_by_count":1,"area":"agents"},{"id":"2609.10548","title":"When Passing Tests Hides Vulnerabilities: An Empirical Study of Silent Failures in Agentic Systems","created":"2026-06-25","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":"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":"2608.23181","title":"CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild","created":"2026-08-24","cited_by_count":0,"area":"agents"},{"id":"2610.06163","title":"Where Did the Repair First Go Wrong? Localizing the Origins of Silent Failures in Agentic Vulnerability Repair","created":"2026-10-05","cited_by_count":0,"area":"agents"}],"next_cursor":null}