DeepVoyager-VL: Incentivizing Vision-in-the-Loop Search for Long-Horizon Multimodal Agents
- 类型:arxiv
- 标识:2608.01827
- 链接:https://arxiv.org/abs/2608.01827
- 主分类:multimodal
- 形态:method
- 被引:0
- 被引来源:Semantic Scholar
- S2被引:0
- 影响力被引:0
- TLDR:DeepVoyager-VL is proposed, a long-horizon multimodal deep-search framework for vision-in-the-loop search that constructs a multimodal event graph to drive data synthesis, yielding problems with intermediate visual dependencies and long reasoning chains.
- 副分类:agent
- 待LLM分类:否
- 标题中文:DeepVoyager-VL:激励视觉在环的搜索以应对长程多模态 Agent
- TLDR中文:本文提出 DeepVoyager-VL,一种面向视觉在环搜索的长程多模态深度搜索框架,通过构建多模态事件图驱动数据合成,从而产出具有中间视觉依赖与长推理链的问题。
- 来源文件:
- /inbox/tom/_candidates/2026-08-04-agent-rag-longcontext-candidates.json
- [S2 enrich]