VideoScout: Learning Agentic Active Exploration with Adaptive Reasoning Pacing for Long Video Understanding
VideoScout is proposed, a multi-turn reasoning agent that instantiates the SEA paradigm through adaptive reasoning pacing and enables efficient traversal of long videos within a bounded visual context window, allowing the agent to access more video content while balancing content analysis depth with reading efficiency.
Weixin Xu, Zhenyu Yang, Bing Wang et al.
· 0 citations