Skywork-R1V4：通过图像与深度研究交织思考实现代理多模态智能
Skywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch
AI总结：
Skywork-R1V4通过交织推理实现多模态代理智能，仅用监督学习在少数据上训练，超越现有模型在多个基准测试中的表现。
摘要：
尽管在多模态代理系统方面取得了近期进展，现有方法往往将图像处理和网络搜索视为独立能力，严重依赖昂贵的强化学习，并缺乏基于真实工具执行轨迹的规划。为解决这些限制，我们提出了Skywork-R1V4，一个具有300亿（A3B）参数的多模态代理模型，它统一了多模态规划、主动图像处理（
英文摘要：
Despite recent progress in multimodal agentic systems, existing approaches often treat image manipulation and web search as disjoint capabilities, rely heavily on costly reinforcement learning, and lack planning grounded in real tool-execution traces. To address these limitations, we present Skywork-R1V4, a 30B (A3B) parameter multimodal agentic model that unifies multimodal planning, active image manipulation ("thinking with images"), deep multimodal search, and, most critically, interleaved reasoning that dynamically alternates between visual operations and external knowledge retrieval. Trained solely via supervised fine-tuning on fewer than 30,000 high-quality, planning-execution-consistent trajectories and validated through stepwise consistency filtering, Skywork-R1V4 achieves state-of-the-art results across perception and multimodal search benchmarks: it scores 66.1 on MMSearch and 67.2 on FVQA, surpassing Gemini 2.5 Flash on all 11 metrics. Skywork-R1V4 exhibits emergent long-horizon reasoning at inference time, successfully orchestrating more than 10 tool calls to solve complex, multi-step tasks. Our results demonstrate that sophisticated agentic multimodal intelligence can be achieved through carefully curated supervised learning alone, without any reliance on reinforcement learning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
