{"type":"link","version":"1.0","title":"OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflows","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/arxiv2508.09124","thumbnail_url":"https://ai-arch.pages.dev/og/arxiv2508.09124.png","thumbnail_width":1200,"thumbnail_height":630}