Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.13964 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915203050897408 |
|---|---|
| author | Han, Siwei Xia, Peng Zhang, Ruiyi Sun, Tong Li, Yun Zhu, Hongtu Yao, Huaxiu |
| author_facet | Han, Siwei Xia, Peng Zhang, Ruiyi Sun, Tong Li, Yun Zhu, Hongtu Yao, Huaxiu |
| contents | Document Question Answering (DocQA) is a very common task. Existing methods using Large Language Models (LLMs) or Large Vision Language Models (LVLMs) and Retrieval Augmented Generation (RAG) often prioritize information from a single modal, failing to effectively integrate textual and visual cues. These approaches struggle with complex multi-modal reasoning, limiting their performance on real-world documents. We present MDocAgent (A Multi-Modal Multi-Agent Framework for Document Understanding), a novel RAG and multi-agent framework that leverages both text and image. Our system employs five specialized agents: a general agent, a critical agent, a text agent, an image agent and a summarizing agent. These agents engage in multi-modal context retrieval, combining their individual insights to achieve a more comprehensive understanding of the document's content. This collaborative approach enables the system to synthesize information from both textual and visual components, leading to improved accuracy in question answering. Preliminary experiments on five benchmarks like MMLongBench, LongDocURL demonstrate the effectiveness of our MDocAgent, achieve an average improvement of 12.1% compared to current state-of-the-art method. This work contributes to the development of more robust and comprehensive DocQA systems capable of handling the complexities of real-world documents containing rich textual and visual information. Our data and code are available at https://github.com/aiming-lab/MDocAgent. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_13964 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding Han, Siwei Xia, Peng Zhang, Ruiyi Sun, Tong Li, Yun Zhu, Hongtu Yao, Huaxiu Machine Learning Document Question Answering (DocQA) is a very common task. Existing methods using Large Language Models (LLMs) or Large Vision Language Models (LVLMs) and Retrieval Augmented Generation (RAG) often prioritize information from a single modal, failing to effectively integrate textual and visual cues. These approaches struggle with complex multi-modal reasoning, limiting their performance on real-world documents. We present MDocAgent (A Multi-Modal Multi-Agent Framework for Document Understanding), a novel RAG and multi-agent framework that leverages both text and image. Our system employs five specialized agents: a general agent, a critical agent, a text agent, an image agent and a summarizing agent. These agents engage in multi-modal context retrieval, combining their individual insights to achieve a more comprehensive understanding of the document's content. This collaborative approach enables the system to synthesize information from both textual and visual components, leading to improved accuracy in question answering. Preliminary experiments on five benchmarks like MMLongBench, LongDocURL demonstrate the effectiveness of our MDocAgent, achieve an average improvement of 12.1% compared to current state-of-the-art method. This work contributes to the development of more robust and comprehensive DocQA systems capable of handling the complexities of real-world documents containing rich textual and visual information. Our data and code are available at https://github.com/aiming-lab/MDocAgent. |
| title | MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2503.13964 |