{"type":"post","id":"workflowarena-executable-workflow-orchestration-05cbd4","slug":"workflowarena-executable-workflow-orchestration-05cbd4","title":"WorkflowArena: Executable Workflow Orchestration","description":"Navers Lab and Einsia AI describe WorkflowArena, a benchmark of 145 long-horizon tasks for testing how LLM-based multi-agent systems organize work and deliver integrated results.","retrieval_nugget":"Navers Lab and Einsia AI describe WorkflowArena, a benchmark of 145 long-horizon tasks for testing how LLM-based multi-agent systems organize work and deliver integrated results. It makes workflow choices observable alongside completed-task acceptance, while showing that high partial scores, added effort, and more workers do not necessarily translate into full delivery.","published_at":"2026-11-14","updated_at":"2026-11-14","record_date":"2026-11-14","date_kind":"published_at","topics":["claude","claude-code"],"entities":["WorkflowArena","Navers Lab","Einsia AI","Claude Opus 5.5","Claude Code","GPT-6 Astra","Sol"],"related_patterns":["agent-economics-moves-to-completed-work"],"novelty_label":"new_fact","what_changed":"The WorkflowArena benchmark page adds results including a 36.95% top Overall Resolved rate and a 6.41-point average gain when Opus-authored workflows are transferred to four executors.","prior_refs":[],"source_url":"https://lab.einsia.ai/workflowarena/home.html","source_urls":["https://lab.einsia.ai/workflowarena/home.html"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:workflowarena-executable-workflow-orchestration-05cbd4","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/workflowarena-executable-workflow-orchestration-05cbd4/","markdown":"https://newruntime.com/posts/workflowarena-executable-workflow-orchestration-05cbd4.md","json":"https://newruntime.com/posts/workflowarena-executable-workflow-orchestration-05cbd4.json"},"markdown_url":"https://newruntime.com/posts/workflowarena-executable-workflow-orchestration-05cbd4.md","next_reads":[{"type":"topic","path":"/topics/claude/","url":"https://newruntime.com/topics/claude/","title":"Claude","reason":"Explore the claude topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/claude.md","json_url":"https://newruntime.com/topics/claude.json"},{"type":"topic","path":"/topics/claude-code/","url":"https://newruntime.com/topics/claude-code/","title":"Claude Code","reason":"Explore the claude-code topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/claude-code.md","json_url":"https://newruntime.com/topics/claude-code.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}