DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911730412552192 |
|---|---|
| author | Deng, Chenlong Deng, Mengjie Wu, Junjie Zeng, Dun Wang, Teng Xie, Qingsong Huang, Jiadeng Ma, Shengjie Zhang, Changwang Wang, Zhaoxiang Wang, Jun Zhu, Yutao Dou, Zhicheng |
| author_facet | Deng, Chenlong Deng, Mengjie Wu, Junjie Zeng, Dun Wang, Teng Xie, Qingsong Huang, Jiadeng Ma, Shengjie Zhang, Changwang Wang, Zhaoxiang Wang, Jun Zhu, Yutao Dou, Zhicheng |
| contents | Existing multimodal retrieval systems excel at semantic matching but implicitly assume that query-image relevance can be measured in isolation. This paradigm overlooks the rich dependencies inherent in realistic visual streams, where information is distributed across temporal sequences rather than confined to single snapshots. To bridge this gap, we introduce DeepImageSearch, a novel agentic paradigm that reformulates image retrieval as an autonomous exploration task. Models must plan and perform multi-step reasoning over raw visual histories to locate targets based on implicit contextual cues. We construct DISBench, a challenging benchmark built on interconnected visual data. To address the scalability challenge of creating context-dependent queries, we propose a human-model collaborative pipeline that employs vision-language models to mine latent spatiotemporal associations, effectively offloading intensive context discovery before human verification. Furthermore, we build a robust baseline using a modular agent framework equipped with fine-grained tools and a dual-memory system for long-horizon navigation. Extensive experiments demonstrate that DISBench poses significant challenges to state-of-the-art models, highlighting the necessity of incorporating agentic reasoning into next-generation retrieval systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_10809 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories Deng, Chenlong Deng, Mengjie Wu, Junjie Zeng, Dun Wang, Teng Xie, Qingsong Huang, Jiadeng Ma, Shengjie Zhang, Changwang Wang, Zhaoxiang Wang, Jun Zhu, Yutao Dou, Zhicheng Computer Vision and Pattern Recognition Information Retrieval Existing multimodal retrieval systems excel at semantic matching but implicitly assume that query-image relevance can be measured in isolation. This paradigm overlooks the rich dependencies inherent in realistic visual streams, where information is distributed across temporal sequences rather than confined to single snapshots. To bridge this gap, we introduce DeepImageSearch, a novel agentic paradigm that reformulates image retrieval as an autonomous exploration task. Models must plan and perform multi-step reasoning over raw visual histories to locate targets based on implicit contextual cues. We construct DISBench, a challenging benchmark built on interconnected visual data. To address the scalability challenge of creating context-dependent queries, we propose a human-model collaborative pipeline that employs vision-language models to mine latent spatiotemporal associations, effectively offloading intensive context discovery before human verification. Furthermore, we build a robust baseline using a modular agent framework equipped with fine-grained tools and a dual-memory system for long-horizon navigation. Extensive experiments demonstrate that DISBench poses significant challenges to state-of-the-art models, highlighting the necessity of incorporating agentic reasoning into next-generation retrieval systems. |
| title | DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories |
| topic | Computer Vision and Pattern Recognition Information Retrieval |
| url | https://arxiv.org/abs/2602.10809 |