CASE: Cost-Aware Stopping for Efficient Long-Video Agents
Long-video agents can actively gather question-relevant evidence, but they typically leave a central decision implicit: when has the agent seen enough to answer? We propose CASE, a plug-in termination framework that frames this decision as policy-conditioned sequential stopping. At each causal checkpoint, CASE combines...
Yi-Ming Du, Cheng-Hao Liu, Zhiyuan Liu et al.
· 0 citations