arXiv:2605.06094v4 Announce Type: replace-cross Abstract: Training VideoLLMs for complex reasoning remains challenging due to sparse sequence level rewards and the lack of fine grained credit assignment over long, temporally grounded reasoning trajectories. While reinforcement learning with verifiable rewards (RLVR) provides reliable supervision, it fails to capture token level contributions, leading to inefficient learning. Conversely, existing self distillation methods offer dense supervision but lack structure and diagnostic specificity, and often interact unstably with reinforcement learni
Source: arXiv cs.AI — read the full report at the original publisher.