ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910981719851008 |
|---|---|
| author | Wang, Qiuchen Ding, Ruixue Chen, Zehui Wu, Weiqi Wang, Shihang Xie, Pengjun Zhao, Feng |
| author_facet | Wang, Qiuchen Ding, Ruixue Chen, Zehui Wu, Weiqi Wang, Shihang Xie, Pengjun Zhao, Feng |
| contents | Understanding information from visually rich documents remains a significant challenge for traditional Retrieval-Augmented Generation (RAG) methods. Existing benchmarks predominantly focus on image-based question answering (QA), overlooking the fundamental challenges of efficient retrieval, comprehension, and reasoning within dense visual documents. To bridge this gap, we introduce ViDoSeek, a novel dataset designed to evaluate RAG performance on visually rich documents requiring complex reasoning. Based on it, we identify key limitations in current RAG approaches: (i) purely visual retrieval methods struggle to effectively integrate both textual and visual features, and (ii) previous approaches often allocate insufficient reasoning tokens, limiting their effectiveness. To address these challenges, we propose ViDoRAG, a novel multi-agent RAG framework tailored for complex reasoning across visual documents. ViDoRAG employs a Gaussian Mixture Model (GMM)-based hybrid strategy to effectively handle multi-modal retrieval. To further elicit the model's reasoning capabilities, we introduce an iterative agent workflow incorporating exploration, summarization, and reflection, providing a framework for investigating test-time scaling in RAG domains. Extensive experiments on ViDoSeek validate the effectiveness and generalization of our approach. Notably, ViDoRAG outperforms existing methods by over 10% on the competitive ViDoSeek benchmark. The code is available at https://github.com/Alibaba-NLP/ViDoRAG. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_18017 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents Wang, Qiuchen Ding, Ruixue Chen, Zehui Wu, Weiqi Wang, Shihang Xie, Pengjun Zhao, Feng Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Information Retrieval Understanding information from visually rich documents remains a significant challenge for traditional Retrieval-Augmented Generation (RAG) methods. Existing benchmarks predominantly focus on image-based question answering (QA), overlooking the fundamental challenges of efficient retrieval, comprehension, and reasoning within dense visual documents. To bridge this gap, we introduce ViDoSeek, a novel dataset designed to evaluate RAG performance on visually rich documents requiring complex reasoning. Based on it, we identify key limitations in current RAG approaches: (i) purely visual retrieval methods struggle to effectively integrate both textual and visual features, and (ii) previous approaches often allocate insufficient reasoning tokens, limiting their effectiveness. To address these challenges, we propose ViDoRAG, a novel multi-agent RAG framework tailored for complex reasoning across visual documents. ViDoRAG employs a Gaussian Mixture Model (GMM)-based hybrid strategy to effectively handle multi-modal retrieval. To further elicit the model's reasoning capabilities, we introduce an iterative agent workflow incorporating exploration, summarization, and reflection, providing a framework for investigating test-time scaling in RAG domains. Extensive experiments on ViDoSeek validate the effectiveness and generalization of our approach. Notably, ViDoRAG outperforms existing methods by over 10% on the competitive ViDoSeek benchmark. The code is available at https://github.com/Alibaba-NLP/ViDoRAG. |
| title | ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2502.18017 |