How I Study AI - Learn AI Papers & Lectures the Easy Way

SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning

Intermediate

Jitesh Jain, Jialuo Li et al.Dec 15arXiv

SAGE is a smart video-watching agent that decides when to answer quickly and when to take multiple steps, just like how people skim or rewind long videos.

#any-horizon reasoning#video agents#temporal grounding

Papers1

SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning