About this paper
A diagnostic benchmark of 180 simulated manipulation configurations evaluates whether embodied systems can combine history-based reasoning, precise execution, and closed-loop environmental feedback, revealing that single-view competence does not transfer to composed tasks.
Embodied intelligence aims to let robots perform complex physical tasks with human-like adaptability and reliability, which requires three complementary capabilities: history-based cognitive reasoning, precise and timely physical execution, and the composition of reasoning and execution through environmental feedback. Yet existing benchmarks either evaluate reasoning and execution within the same tasks or assess them separately without their composition, so they reveal little about whether a failure comes from reasoning, execution, or their composition. We introduce Mind2Act World, a diagnostic benchmark of 30 simulated manipulation tasks from five real-world application domains. Each task…
embodied intelligencemultimodal agentsvision-language-action models (VLAs)world-action models (WAMs)end-to-end policiesclosed-loop tasksdiagnosis harnesstask statesimulated manipulation tasks
- Upvotes
- 23
- Authors
- 43
- Published
- Nov 19, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
Mind2Act World: A Diagnostic Benchmark for Embodied Mind, Physical Action, and Mind-Action Composition in Robotic Manipulation was first seen on Hugging Face · Daily papers on Nov 20, 2026. Since then it has appeared in 29 checks on 3 different days. Its best position was #1 of 30, reached on Nov 20, 07:29 UTC. It is #2 right now, holding steady at #2 over the last 6 checks.