PhysTool-Bench shows leading MLLMs identify at most 58.7% of tools in scenes and complete only 21% of physical tool-use queries end-to-end.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Beyond APIs: Probing the Limits of MLLMs in Physical Tool Use
PhysTool-Bench shows leading MLLMs identify at most 58.7% of tools in scenes and complete only 21% of physical tool-use queries end-to-end.