让视频推理模型像人一样灵活选择观看时长，提升长视频理解能力。
SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning
- 设计多轮交互式代理系统，短任务单次处理，长视频分步推理。
- 通过强化学习训练，使模型在超长视频上准确率提升8.2%。
- 构建700秒以上的评测集，适合真实娱乐场景的视频理解评估。
人类天然具备跨时长推理能力，能根据任务需要决定是快速浏览还是完整观看长视频。现有先进模型通常需一次性处理大量帧，资源消耗大，难以灵活应对不同长度视频。为此，我们提出SAGE系统，支持多轮推理：简单任务单次完成，复杂长视频分步处理。设计基于Gemini-2.5-Flash的合成数据生成流程，训练核心控制器SAGE-MM；并提出有效强化学习后训练方法，赋予其跨时长推理能力。构建包含平均时长超过700秒的SAGE-Bench评测集，用于真实娱乐场景下的视频理解评估。实验验证表明，系统在开放问答任务上性能最高提升6.1%，在超过10分钟的视频上提升达8.2%。
原文摘要 · Abstract (English)
As humans, we are natural any-horizon reasoners, i.e., we can decide whether to iteratively skim long videos or watch short ones in full when necessary for a given task. With this in mind, one would expect video reasoning models to reason flexibly across different durations. However, SOTA models are still trained to predict answers in a single turn while processing a large number of frames, akin to watching an entire long video, requiring significant resources. This raises the question: Is it possible to develop performant any-horizon video reasoning systems? Inspired by human behavior, we first propose SAGE, an agent system that performs multi-turn reasoning on long videos while handling simpler problems in a single turn. Secondly, we introduce an easy synthetic data generation pipeline using Gemini-2.5-Flash to train the orchestrator, SAGE-MM, which lies at the core of SAGE. We further propose an effective RL post-training recipe essential for instilling any-horizon reasoning ability in SAGE-MM. Thirdly, we curate SAGE-Bench with an average duration of greater than 700 seconds for evaluating video reasoning ability in real-world entertainment use cases. Lastly, we empirically validate the effectiveness of our system, data, and RL recipe, observing notable improvements of up to 6.1% on open-ended video reasoning tasks, as well as an impressive 8.2% improvement on videos longer than 10 minutes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。