robotics
Choosing the Right Tool Did Not Mean Finishing the Task
HumanoidToolBench spans 18 tasks and exposes a gap from selection to mobile execution.
Summary
HumanoidToolBench spans 18 tasks and exposes a gap from selection to mobile execution.
HumanoidToolBench combines tool choice, manipulation and locomotion across 18 simulated tasks, with ToolBook providing 3,100 demonstrations from simulation and a real Unitree G1. Seven simulated policies and three real-robot policies showed a substantial gap between selecting a suitable tool and completing the task. Focused probes also found lower selection accuracy on unseen tools and continued execution under unrelated instructions. The benchmark is a controlled evaluation, not a safety certification for humanoid deployment.
Why it matters
HumanoidToolBench spans 18 tasks and exposes a gap from selection to mobile execution.
Limits and context
- The benchmark is a controlled evaluation, not a safety certification for humanoid deployment.
Key claims
HumanoidToolBench spans 18 tasks and exposes a gap from selection to mobile execution.
Qualification: The benchmark is a controlled evaluation, not a safety certification for humanoid deployment.
Evidence: source-2026-10-02-013
Sources
- arXiv preprint 2610.02089arXiv · primary research
Corrections
No corrections have been recorded for this story.