# EVAThink: Evidence Sufficiency-Guided Training for Adaptive Thinking in Video Understanding > Source: > Published: 2026-11-11 05:30:09+00:00 Under a fixed frame budget, video understanding with vision-language models (VLMs) depends on whether the sampled frames provide sufficient evidence for the question. Sufficient frame evidence supports direct answering, whereas less informative observations may benefit from reasoning that connects t