Preprint
Aug 2026
DeepVoyager-VL: Incentivizing Vision-in-the-Loop Search for Long-Horizon Multimodal Agents
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.
Huan-Yao Zhang, Jie-Peng Zhou, Ru Zhao et al.
· 0 citations