{"ID":2923493,"CreatedAt":"2026-06-02T04:05:25.881865328Z","UpdatedAt":"2026-06-04T17:52:58.968687531Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.02564","arxiv_id":"2606.02564","title":"VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization","abstract":"The recent \"Reasoning with Video\" paradigm utilizes Video Generation Models (VGMs) to generate temporally coherent visual trajectories to complete reasoning tasks. Although state-of-the-art VGMs excel at visual quality, they often struggle to understand and follow task-specific rules, leading to logical failures across diverse reasoning scenarios. Existing efforts try to utilize Vision-Language Models (VLMs) as problem pre-solvers to produce or refine textual guidance for the VGM. However, textual descriptions fail to capture intricate spatiotemporal details, and VGMs often struggle to faithfully execute fine-grained or long-tail instructions even with a valid plan. While VLMs struggle as solvers, they possess strong perception capabilities to evaluate process-constraint satisfaction and final-goal achievement. Leveraging this strength, we introduce a paradigm shift that transitions the role of VLMs to \"teachers\". Specifically, a VLM teacher extracts task-specific rules to formulate differentiable rewards, guiding a VGM Reasoner via test-time online optimization of a lightweight LoRA module. This strategy enables adaptive test-time optimization and extends the reasoning capabilities beyond the VGM's intrinsic boundaries. Evaluations on symbolic (VBVR-Bench) and general-purpose (RULER-Bench) video reasoning benchmarks show that the proposed method yields a 16.7-point average performance gain, outperforming the VLM-as-Solver paradigm (+0.4 points) and Best-of-N scaling (+2.2 points) by a large margin at comparable test-time cost. These findings reveal that integrating VLMs as test-time teachers offers a promising paradigm for achieving generalizable video reasoning. Project Page: https://VLM-as-Teacher.github.io/","short_abstract":"The recent \"Reasoning with Video\" paradigm utilizes Video Generation Models (VGMs) to generate temporally coherent visual trajectories to complete reasoning tasks. Although state-of-the-art VGMs excel at visual quality, they often struggle to understand and follow task-specific rules, leading to logical failures across...","url_abs":"https://arxiv.org/abs/2606.02564","url_pdf":"https://arxiv.org/pdf/2606.02564v1","authors":"[\"Junhao Cheng\",\"Liang Hou\",\"Tianxiong Zhong\",\"Xin Tao\",\"Pengfei Wan\",\"Kun Gai\",\"Jing Liao\"]","published":"2026-06-01T17:54:26Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Language Model\",\"LoRA\"]","has_code":false}