Mind2ActWorld: Tsinghua-led benchmark dissects why robots fail, step by step

机器之心 · wechat · 2026-11-22

Amid the 'VLA/WAM dead, foundation-model agents rising' debate, Tsinghua mmlab@SIGS and Velabot AI plus 16 institutions released Mind2ActWorld: 30 tasks, 180 configs, testing 'mind' (memory/reasoning), 'act' (physical execution), and their composition separately, with per-episode failure attribution and diagnosis cards. Across 9 systems and 56,700 sim episodes, the best agent (GPT-6 Astra) scores 52.7% on Mind, 39.0% on Act, only 12.0% on Mind2Act; end-to-end policies top out at 3.6%. Most failures break in physical execution, not coordination. The report also derives data/tooling fixes from breakpoints and counts hidden costs: 11-35.6s per agent call, $25.13 per episode API cost. Verdict: task-specific models plus self-evolution loops, not one winner.

Related event: Tsinghua and 16 Institutions Release Mind2Act World Robot Diagnostic Benchmark(2 posts)→

Original post →

More from Embodied

Embodied channel →