{"total":14,"rows":[{"id":"2508.18106","title":"A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code","created":"2025-08-25","cited_by_count":14,"area":null},{"id":"2605.26548","title":"SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?","created":"2026-05-26","cited_by_count":9,"area":null},{"id":"2606.04460","title":"CyberGym-E2E: Scalable Real-World Benchmark for AI Agents' End-to-End Cybersecurity Capabilities","created":"2026-06-03","cited_by_count":8,"area":null},{"id":"2609.04075","title":"PatchBench: Evaluating AI Agents for Vulnerability Patching","created":"2026-09-03","cited_by_count":2,"area":null},{"id":"2610.07557","title":"CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?","created":"2026-10-06","cited_by_count":2,"area":null},{"id":"2607.24780","title":"LivingArena: Do LLMs Know What Other LLMs Don't? Peer-Probing as Scalable Evaluation","created":"2026-06-19","cited_by_count":1,"area":null},{"id":"2601.21070","title":"Towards Comprehensive Benchmarking Infrastructure for LLMs In Software Engineering","created":"2026-01-28","cited_by_count":0,"area":null},{"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":"2605.21615","title":"ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2607.16660","title":"From Adoption to Deployment: A Qualitative Study on AI Integration in Software Development Practice","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2607.27030","title":"HoF-Bench: Rediscovering Real AI-Discovered CVEs Without Frontier Models","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.21107","title":"Large Language Models at the Intersection of Software Engineering and Software Security:An Evidence-Centered Structured Survey and Research Agenda","created":"2026-08-21","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":"2610.06584","title":"Does AI Help Cyber Attackers or Defenders? Evidence from Nonpublic Vulnerabilities and Subsequent Attacks","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}