CVAIAug 3

DeepVoyager-VL: Incentivizing Vision-in-the-Loop Search for Long-Horizon Multimodal Agents

arXiv:2608.0182729.3
Predicted impact top 1% in CV · last 90 daysOriginality Incremental advance
AI Analysis

This work addresses the limitation of MLLMs in open-world, knowledge-intensive tasks by enabling long-horizon, visually-guided search, benefiting multimodal AI agents and search systems.

DeepVoyager-VL introduces a long-horizon multimodal deep-search framework that integrates visual evidence into intermediate reasoning steps, enabling vision-in-the-loop search. The method improves performance across ten multimodal search benchmarks, achieving state-of-the-art results.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes