# DeepVoyager-VL：为长程多模态智能体激励视觉在环搜索

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-08-03 08:00
- AIHOT 分数：53
- AIHOT 链接：https://aihot.virxact.com/items/cmseazfg10k6bro2e8gswhcpf
- 原文链接：https://arxiv.org/abs/2608.01827

## AI 摘要

DeepVoyager-VL 提出一种面向视觉在环搜索的长程多模态深度搜索框架，让视觉证据驱动持续检索而非仅停留在输入或答案阶段。该方法通过多模态事件图驱动数据合成，生成含中间视觉依赖与长推理链的问题，并设计主动视觉获取与按需图像加载的智能体框架，在合成数据上微调模型而无需强化学习。在十个多模态搜索基准上的实验验证了其有效性。

## 正文

Multimodal large language models (MLLMs) have advanced visual understanding and reasoning, yet their static parametric knowledge limits their ability to address knowledge-intensive and dynamically evolving open-world problems. To move beyond this limitation, multimodal deep search has emerged as a key direction for open-world information access, evolving from single-turn factual retrieval toward long-horizon, multi-turn search guided by visual evidence. However, existing methods typically confine vision to the input or answer stage, overlooking its role in intermediate reasoning, and lack designs tailored to long-horizon interaction. Consequently, visual evidence rarely drives continued retrieval, constraining both interaction depth and reasoning span. To address these limitations, we propose DeepVoyager-VL, a long-horizon multimodal deep-search framework for vision-in-the-loop search. Specifically, we construct a multimodal event graph to drive data synthesis, yielding problems with intermediate visual dependencies and long reasoning chains. We then design an agent framework for active visual acquisition and on-demand image loading. Finally, we fine-tune models on the synthesized data without reinforcement learning. Extensive experiments across ten multimodal search benchmarks demonstrate the effectiveness of our method.