EVA：面向端到端视频智能体的高效强化学习框架
EVA: Efficient Reinforcement Learning for End-to-End Video Agent
把视频理解从「被动识别整段视频」改成「先规划再看」的智能体范式：用 SFT+KTO+GRPO 三阶段训练让 MLLM 自主决定看哪些帧、何时看，可直接复用到长视频问答与高效视频推理中。
原文依据 EVA autonomously decides what to watch, when to watch, and how to watch, achieving query-driven and efficient video understanding.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于多模态大语言模型的视频理解仍然具有挑战性，因为视频的词元序列很长，其中包含大量时序依赖关系和冗余帧。现有方法通常把多模态大语言模型当作被动的识别器，处理整段视频或均匀采样的帧，缺乏自适应推理。近期基于智能体的方法引入了外部工具，但仍依赖人工设计的工作流和感知优先的策略，导致在长视频上效率低下。我们提出 EVA，一个面向端到端视频智能体的高效强化学习框架，通过迭代的总结—规划—行动—反思推理实现先规划后感知。EVA 自主决定看什么、何时看以及如何看，从而实现查询驱动且高效的视频理解。为训练这样的智能体，我们设计了一个简单而有效的三阶段学习流程——包括监督微调（SFT）、Kahneman-Tversky 优化（KTO）和组相对策略优化（GRPO）——在监督模仿与强化学习之间建立衔接。我们进一步为每个阶段构建了高质量数据集，支撑稳定且可复现的训练。我们在六个视频理解基准上评估 EVA，展示了其全面的能力。与现有基线相比，EVA 相较通用多模态大语言模型基线取得 6–12% 的显著提升，并在此前自适应智能体方法的基础上进一步提升 1–3%。
英文原文摘要 1484 字符
Video understanding with multimodal large language models (MLLMs) remains challenging due to the long token sequences of videos, which contain extensive temporal dependencies and redundant frames.Existing approaches typically treat MLLMs as passive recognizers, processing entire videos or uniformly sampled frames without adaptive reasoning.Recent agent-based methods introduce external tools, yet still depend on manually designed workflows and perception-first strategies, resulting in inefficiency on long videos. We present EVA, an Efficient Reinforcement Learning framework for End-to-End Video Agent, which enables planning-before-perception through iterative summary-plan-action-reflection reasoning.EVA autonomously decides what to watch, when to watch, and how to watch, achieving query-driven and efficient video understanding.To train such agents, we design a simple yet effective three-stage learning pipeline--comprising supervised fine-tuning (SFT), Kahneman-Tversky Optimization (KTO), and Group Relative Policy Optimization (GRPO)--that bridges supervised imitation and reinforcement learning.We further construct high-quality datasets for each stage, supporting stable and reproducible training.We evaluate EVA on six video understanding benchmarks, demonstrating its comprehensive capabilities. Compared with existing baselines, EVA achieves a substantial improvement of 6--12% over general MLLM baselines and a further 1--3% gain over prior adaptive agent methods.