AI RESEARCH
When to Think and When to Look: Uncertainty-Guided Lookback
arXiv CS.CL
•
ArXi:2511.15613v3 Announce Type: replace-cross Test-time thinking (that is, generating explicit intermediate reasoning chains) is known to boost performance in large language models and has recently shown strong gains for large vision language models (LVLMs). However, despite these promising results, there is still no systematic analysis of how thinking actually affects visual reasoning.