{"type":"link","version":"1.0","title":"Agent-Diff: Benchmarking LLM Agents on Enterprise API Tasks via Code Execution with State-Diff-Based 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/arxiv2602.11224","thumbnail_url":"https://ai-arch.pages.dev/og/arxiv2602.11224.png","thumbnail_width":1200,"thumbnail_height":630}