@inproceedings{jin-etal-2026-videocurl,
    title = "{V}ideo{C}u{RL}: Video Curriculum Reinforcement Learning with Orthogonal Difficulty Decomposition",
    author = "Jin, Hongbo  and
      Lin, Kuanwei  and
      Zhang, Wenhao  and
      Jin, Yichen  and
      Li, Ge",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.953/",
    pages = "20832--20845",
    ISBN = "979-8-89176-390-6",
    abstract = "Reinforcement Learning (RL) is crucial for empowering Video-LLMs with complex spatiotemporal reasoning. However, current RL paradigms predominantly rely on random data shuffling or naive curriculum strategies based on scalar difficulty metrics. We argue that scalar metrics fail to disentangle two orthogonal challenges in video understanding: Visual-Temporal Perception Load and Cognitive Reasoning Depth. To address this, we propose VideoCuRL, a novel framework that decomposes difficulty into these two axes. We employ efficient, training-free proxies{---}optical flow/keyframe entropy for visual complexity and Calibrated Surprisal for cognitive complexity{---}to map data onto a 2D curriculum grid. A competence-aware Diagonal Wavefront strategy then schedules training from base alignment to complex reasoning. Furthermore, we introduce Dynamic Sparse KL and Structured Revisiting to stabilize training against reward collapse and catastrophic forgetting. Extensive experiments show that VideoCuRL surpasses strong RL baselines on reasoning (+2.5{\%} on VSI-Bench) and perception (+2.9{\%} on VideoMME) tasks. Notably, VideoCuRL eliminates the prohibitive inference overhead of generation-based curricula, offering a scalable solution for robust video post-training."
}