跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-08AI 評分45

OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Video

OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Video

AI 導讀

OneSearch-VL 提出以 Visually Grounded Evidence Graph(VGEG)為核心的統一多模態深度研究智能體,涵蓋單圖、多圖及影片研究。

正文

Published on Oct 8

Authors:

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Single-image, multi-image, and video deep research require different visual operations but share a workflow of visual grounding, external retrieval, and fact composition. A key challenge is to preserve the dependencies linking localized visual anchors, entity relations, source-supported facts, and answer-producing operations. We introduce OneSearch-VL, a unified agent centered on the Visually Grounded Evidence Graph (VGEG), which encodes these dependencies as a shared task-level reference for data construction, process supervision, and operation-level evaluation. Our VGEG-based data engine constructs and verifies multi-image and video questions and filters expert trajectories. Using these data, we assemble OneSearch-VL-SFT-110K and OneSearch-VL-RL-10K for SFT and RL, respectively. We further derive the Evidence-aware Visual-Grounded Rubric reward (EVGR) from VGEG annotations to supervise evidence traceability and visual grounding during RL. For fine-grained evaluation, we construct OneSearch-MI-Bench and OneSearch-Video-Bench, organizing questions by the research operations encoded in their VGEGs. Experiments show that OneSearch-VL-8B improves over Qwen3-VL-8B with tool access by 20.2 and 17.6 percentage points on the two new benchmarks, respectively, while also achieving substantial gains across 7 image benchmarks and VideoDR. Project repository: https://github.com/appletea233/OneSearch-VL

View arXiv page View PDF Project page GitHub 2 Add to collection

Get this paper in your agent:

hf papers read 2610.12419

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.12419 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.12419 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.12419 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co