{"type":"link","version":"1.0","title":"Benchmarking the Benchmarks: A Validity Audit of Tool-Calling Evaluation","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/arxiv2607.02577","thumbnail_url":"https://ai-arch.pages.dev/og/arxiv2607.02577.png","thumbnail_width":1200,"thumbnail_height":630}