Recent progress in foundation models has shifted toward agentic behavior involving multi-step reasoning and tool use. However, open-source efforts largely focus on text-dominant settings, leaving long-horizon multimodal tasks underexplored. This gap is evident in video tasks requiring sustained temporal understanding and iterative interaction. We present InternVideo3, a framework enhancing these capabilities via Multimodal Contextual Reasoning (MCR). MCR treats understanding as a closed-loop process over a shared, evolving context containing observations, instructions, reasoning, tool actions, and memory. This frames long-video understanding as evidence accumulation and verification. To ensure efficiency, we introduce Multimodal Multi-head Latent Attention (M^2LA), a token-preserving reparameterization compressing KV-cache states while retaining the full token stream. Our staged training includes continued pretraining, short-to-long supervised fine-tuning, rule-based reinforcement learning, and on-policy distillation. Experiments show InternVideo3 achieves strong performance on benchmarks like Video-MME, MLVU, and EgoSchema. We further instantiate the model as a video agent with retrieval tools, demonstrating robust evidence-grounded behavior. Our results suggest that efficient context handling and closed-loop reasoning are vital for adapting open multimodal models toward long-horizon visually grounded agency.

翻译：近期基础模型的研究进展已转向涉及多步推理与工具使用的智能体行为。然而，开源工作主要聚焦于文本主导场景，长期多模态任务仍未得到充分探索。这一差距在需要持续性时序理解与迭代交互的视频任务中尤为明显。我们提出InternVideo3框架，通过多模态上下文推理（MCR）增强此类能力。MCR将理解过程视为基于共享演进上下文的闭环流程，该上下文包含观测、指令、推理、工具动作与记忆。这使得长视频理解被重构为证据积累与验证过程。为确保效率，我们引入多模态多头潜注意力（M^2LA），这是一种保留完整令牌流的令牌保持型重参数化方法，可压缩KV缓存状态。阶段性训练包含持续预训练、短时到长时监督微调、基于规则的强化学习及在线策略蒸馏。实验表明，InternVideo3在Video-MME、MLVU与EgoSchema等基准测试中取得强劲性能。我们进一步将该模型实例化为配备检索工具的视频智能体，展现出稳健的基于证据的行为。研究结果表明，高效的上下文处理与闭环推理对于推动开放多模态模型向长期视觉导向的智能体化发展至关重要。