AI RESEARCH
Do Thought Streams Matter? Evaluating Reasoning in Gemini Vision-Language Models for Video Scene Understanding
arXiv CS.CV
•
ArXi:2604.11177v1 Announce Type: new We benchmark how internal reasoning traces, which we call thought streams, affect video scene understanding in vision-language models. Using four configurations of Google's Gemini 2.5 Flash and Flash Lite across scenes extracted from 100 hours of video, we ask three questions: does thinking lead to better outputs, where do the gains stop, and what do these models actually think about? We