Huaxing Liu
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper deconstructs latent visual reasoning tokens into components and finds that the performance gains are primarily due to boundary markers and attention patterns, not the tokens' ability to encode visual evidence.
The paper argues that observed gains in multimodal agents using tools may be due to learning tool-calling patterns rather than genuine capability expansion, finding that tool access provides little consistent aggregate improvement.
Papers
Do Multimodal Agents Really Benefit from Tool Use? A Systematic Study of Capability Gains
Garvin Guo, Donglei Yu, Yu Chen, Xiang Wang +5 more
The paper argues that observed gains in multimodal agents using tools may be due to learning tool-calling patterns rather than genuine capability expansion, finding that tool access provides little co…