{"type":"link","version":"1.0","title":"ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use","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/arxiv2501.02506","thumbnail_url":"https://ai-arch.pages.dev/og/arxiv2501.02506.png","thumbnail_width":1200,"thumbnail_height":630}