{"type":"link","version":"1.0","title":"Sec-bench: automated benchmarking of llm agents on real-world software security tasks","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/arxiv2506.11791","thumbnail_url":"https://ai-arch.pages.dev/og/arxiv2506.11791.png","thumbnail_width":1200,"thumbnail_height":630}