OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents
From Daily Paper Cast by Jingwen Liang, Gengyu Wang
May 8, 2026 · 25 min · Episode 1839
About this episode
This episode discusses OpenSearch-VL, an open-source recipe for training multimodal search agents using reinforcement learning.
🤗 Upvotes: 84 | cs.CV Authors: Shuang Chen, Kaituo Feng, Hangting Chen, Wenxuan Huang, Dasen Dai, Quanxin Shou, Yunlong Lin, Xiangyu Yue, Shenghua Gao, Tianyu Pang Title: OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents Arxiv: http://arxiv.org/abs/2605.05185v1 Abstract: 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 entity rewriting, and source-anchor visual grounding, which jointly reduce shortcuts and one-step retrieval collapse. Based on this pipeline, we curate two training datasets, SearchVL-SFT-36k for SFT and…
Topics covered
- multimodal search
- reinforcement learning
- training data
- evidence verification
- active perception
- deep search
Keywords
- OpenSearch-VL
- multimodal agents
- training datasets
- Wikipedia path sampling
- evidence verification
- active search
- deep search
More episodes of Daily Paper Cast
- EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments · June 13, 2026 · 24 min
- MiniMax Sparse Attention · June 13, 2026 · 26 min
- SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning · June 13, 2026 · 23 min
- InterleaveThinker: Reinforcing Agentic Interleaved Generation · June 13, 2026 · 21 min
- FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents · June 13, 2026 · 23 min
- Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? · June 13, 2026 · 20 min
Explore listener stats, chart rankings, contacts and more on the Daily Paper Cast podcast page.