Microsoft's MMCTAgent tackles long videos with a Planner-Critic loop
Microsoft Research just introduced MMCTAgent, an open-source framework built on AutoGen to reason across long videos and massive image libraries. Instead of relying on one-shot answers, it deploys Planner and Critic agents to break down queries, trigger computer vision tools, and cross-check evidence. On the MM-Vet benchmark, it pushed GPT-4V's accuracy from 60.20% to 74.24%.