Preprint
Aug 2026
Paint What You See: Benchmarking Dexterous Visual Tool Use in Multimodal Agents
EASEL is proposed, a benchmark evaluating a controlled instance of dexterous visual tool use that adopts reference-guided visual reconstruction as its primary proxy task: the agent incrementally paints a canvas to match a reference image.
Shudong Liu, Dong-Yang Chen, En-Ci Zhang et al.
· 0 citations