AI RESEARCH
Active Reasoning Vision-Language Models via Sequential Experimental Design
arXiv CS.LG
•
ArXi:2605.01345v1 Announce Type: cross Visual perception in modern Vision-Language Models (VLMs) is constrained by a fundamental perceptual bandwidth bottleneck: a broad field of view inevitably sacrifices the fine-grained details necessary for complex reasoning. Inspired by the classical paradigms of active vision and information foraging, we frame overcoming this limitation as a sequential decision-making process. We formalise this process through the lens of the sequential Bayesian optimal experimental design (S-BOED) problem.