OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents
Deep search has become a crucial capability for frontier multimodal agents, enabling models to solve complex questions through active search, evidence verification, and multi-step reasoning. Despite rapid progress, top-tier multimodal search agents remain difficult to reproduce, largely due to the absence of open high-quality training data, transparent trajectory synthesis pipelines, or detailed training recipes. To this end, we introduce OpenSearch-VL, a fully open-source recipe for training frontier multimodal deep search agents with agentic reinforcement learning. First, we curated a dedicated pipeline to construct high-quality training data through Wikipedia path sampling, fuzzy entit...
| Authors | Shuang Chen, Kaituo Feng, Hangting Chen et al. |
|---|---|
| Primary category | cs.CV |
| Published | 6 May 2026 |
| Last updated at source | 6 May 2026 |
Connected in the knowledge graph
- OpenSearch-VL/Search-VL-SFT-36KDataset · cited by
- OpenSearch-VL/Search-VL-RL-8KDataset · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.