works on
chain-of-thought fine-tuning 1efficiency 1implicit visual tools 1multimodal large language models 1self-regulated inference 1tool usage optimization 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.CV2026

Beyond the Eye: Efficient Multimodal Reasoning via Self-Regulated Implicit Visual Tools

Xiuwei Chen, Quanlin Chen, Wentao Hu +8

The paper introduces Beyond the Eye (BEE), an implicit visual‑tool framework for multimodal large language models that learns to self‑regulate when to invoke visual tools, reducing…